[
  {
    "reward_this_epoch": -2.062623970339174,
    "equal_rewards": -2.0464833529585715,
    "random_rewards": -0.7523101927769723,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0093423539461384,
    "equal_rewards": -2.0269163626536626,
    "random_rewards": -1.1500626771912132,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0222703315694623,
    "equal_rewards": -2.0038283147942515,
    "random_rewards": -2.4803363301629258,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0138226931132706,
    "equal_rewards": -2.0223897486925835,
    "random_rewards": -1.1865883133887245,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9977954152068502,
    "equal_rewards": -2.0478490124360245,
    "random_rewards": -1.8239062782854274,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.028413781138782,
    "equal_rewards": -2.0158546560915824,
    "random_rewards": -2.205458895188297,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0157966256957804,
    "equal_rewards": -2.0611926557863374,
    "random_rewards": -1.7864008283752089,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.009409017888375,
    "equal_rewards": -2.062700368934328,
    "random_rewards": -2.588521125318625,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0078835458469566,
    "equal_rewards": -2.045175138778028,
    "random_rewards": -2.3880189561503142,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9946101794984963,
    "equal_rewards": -2.017030414468136,
    "random_rewards": -1.4321668931587341,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9925175982595533,
    "equal_rewards": -2.002580503112311,
    "random_rewards": -2.511816728502174,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9876513936096831,
    "equal_rewards": -2.0333580174963624,
    "random_rewards": -2.2697326284343586,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.015426695417723,
    "equal_rewards": -2.0352503793030516,
    "random_rewards": -2.078162171984305,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004395561625617,
    "equal_rewards": -2.024995824731313,
    "random_rewards": -1.5094576370399775,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0505873758460593,
    "equal_rewards": -2.0232120670768037,
    "random_rewards": -1.042781211367528,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0246754203051243,
    "equal_rewards": -2.017583547219762,
    "random_rewards": -1.91405663525431,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.044784743259756,
    "equal_rewards": -2.0196977460659062,
    "random_rewards": -1.5018660277465496,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9942474538600916,
    "equal_rewards": -2.0043455237892562,
    "random_rewards": -2.0385470336182894,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9939878828114384,
    "equal_rewards": -2.026592962994009,
    "random_rewards": -1.6235559056760076,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0238245840023756,
    "equal_rewards": -2.0402619075074595,
    "random_rewards": -2.4048892665775656,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0438277323166854,
    "equal_rewards": -2.0184639004579417,
    "random_rewards": -2.512079159755189,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9954352252848677,
    "equal_rewards": -2.0454711765970943,
    "random_rewards": -1.6313649256938825,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0405937283889006,
    "equal_rewards": -2.0056913578243454,
    "random_rewards": -1.4671687399724773,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0115342040152027,
    "equal_rewards": -2.015606545285883,
    "random_rewards": -1.7359055199512037,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9962459663058931,
    "equal_rewards": -2.006359120487266,
    "random_rewards": -1.4610372175069608,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9972153788022005,
    "equal_rewards": -2.029822329488933,
    "random_rewards": -2.502281883109415,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0243547827435786,
    "equal_rewards": -2.0409818542333404,
    "random_rewards": -2.5190095510220423,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.032316137690389,
    "equal_rewards": -2.02810286841974,
    "random_rewards": -2.5041743730617565,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.054437973227234,
    "equal_rewards": -2.0266362480596145,
    "random_rewards": -1.800756737452407,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9932114242869634,
    "equal_rewards": -2.025481787504994,
    "random_rewards": -1.3319871869628856,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.009777173233669,
    "equal_rewards": -2.034821248759079,
    "random_rewards": -2.385122727141323,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.043730269434198,
    "equal_rewards": -2.038474130075987,
    "random_rewards": -2.2233224865791286,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0170472977030864,
    "equal_rewards": -2.024796158123946,
    "random_rewards": -1.1783161711932937,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0336627046760545,
    "equal_rewards": -1.993583499170077,
    "random_rewards": -1.7432737450101938,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0106528407777846,
    "equal_rewards": -2.0430527376906165,
    "random_rewards": -1.6447531119019914,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0232819857786475,
    "equal_rewards": -2.0078694181128514,
    "random_rewards": -2.085406182319625,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0179198834613823,
    "equal_rewards": -2.0446883484678713,
    "random_rewards": -2.118079133155718,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.030964995667723,
    "equal_rewards": -2.0596395405051693,
    "random_rewards": -1.7772496349082936,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.064257698539362,
    "equal_rewards": -2.0273815601556873,
    "random_rewards": -2.504565388716615,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.02529321839814,
    "equal_rewards": -2.043057622722531,
    "random_rewards": -1.487811651900261,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.031249820217046,
    "equal_rewards": -2.0258994273241893,
    "random_rewards": -1.4834391306307833,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0122284523880816,
    "equal_rewards": -2.06279890991619,
    "random_rewards": -1.3664227640187525,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.023697742439791,
    "equal_rewards": -2.0311067928362156,
    "random_rewards": -1.315897497643673,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.039427824327102,
    "equal_rewards": -2.0030913132842594,
    "random_rewards": -1.7756758371246366,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.01057543676096,
    "equal_rewards": -2.048001894920355,
    "random_rewards": -1.3565406784450962,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0143644313227744,
    "equal_rewards": -2.0307845511369567,
    "random_rewards": -1.2029166361836119,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0268403398880763,
    "equal_rewards": -2.061528173636315,
    "random_rewards": -1.5237101076697435,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0671570651145963,
    "equal_rewards": -2.026203369628908,
    "random_rewards": -2.6722332563834357,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.042883276978424,
    "equal_rewards": -2.0381653406251528,
    "random_rewards": -1.324042915095295,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0334140020479428,
    "equal_rewards": -2.007724279957878,
    "random_rewards": -2.0627404498101187,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.98986406259364,
    "equal_rewards": -2.038312881580946,
    "random_rewards": -1.669923823942982,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0113265912271485,
    "equal_rewards": -2.0526329428008188,
    "random_rewards": -1.1929854194951024,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0617985162568364,
    "equal_rewards": -2.0287652743775584,
    "random_rewards": -1.9002832793973097,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0192565570285024,
    "equal_rewards": -2.034781273466582,
    "random_rewards": -2.9845547211280414,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.018491025489628,
    "equal_rewards": -2.0417258711139015,
    "random_rewards": -1.9058756206601326,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0280335179323647,
    "equal_rewards": -2.052837010758561,
    "random_rewards": -1.9611461767897413,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0089135294220473,
    "equal_rewards": -2.043696525508292,
    "random_rewards": -1.6609530279734073,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0380854027720465,
    "equal_rewards": -2.0050119667675577,
    "random_rewards": -1.4836237742745522,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.00638988121031,
    "equal_rewards": -2.0689708994113425,
    "random_rewards": -2.2660952580663443,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0591492912939495,
    "equal_rewards": -2.0288155180987206,
    "random_rewards": -2.672098487251973,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0279728824117997,
    "equal_rewards": -2.0156067024552646,
    "random_rewards": -2.197241457665996,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.018747687516017,
    "equal_rewards": -2.0605570633520625,
    "random_rewards": -1.4974893770349456,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.029855920939592,
    "equal_rewards": -2.0323899449754737,
    "random_rewards": -1.4684251513717643,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.001036407671909,
    "equal_rewards": -2.0216265878862596,
    "random_rewards": -1.763588509438681,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0082244303447583,
    "equal_rewards": -2.064069813932769,
    "random_rewards": -2.5686465022808544,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.038956955005989,
    "equal_rewards": -2.0260159743288355,
    "random_rewards": -1.7661482060748934,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0398279951726628,
    "equal_rewards": -2.006519078679803,
    "random_rewards": -0.8773063076236433,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.993935778991636,
    "equal_rewards": -2.0369143509532845,
    "random_rewards": -1.9293419778170597,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9939502274230443,
    "equal_rewards": -2.0267196927815165,
    "random_rewards": -1.6243470045342607,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.066525691332929,
    "equal_rewards": -2.027848635807005,
    "random_rewards": -1.807729633788277,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.037586110122111,
    "equal_rewards": -2.025020654568936,
    "random_rewards": -2.805528494736539,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0264211542133244,
    "equal_rewards": -2.0096531473080574,
    "random_rewards": -1.0466309448578086,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9830973055528516,
    "equal_rewards": -2.0215572124198506,
    "random_rewards": -1.7802717273432371,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9994239595268772,
    "equal_rewards": -2.0319306145242546,
    "random_rewards": -2.535753521009751,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.058311940609771,
    "equal_rewards": -2.03624871246053,
    "random_rewards": -1.3409442740593736,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007978870505587,
    "equal_rewards": -2.066107551767632,
    "random_rewards": -2.01030898248695,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0134125766820734,
    "equal_rewards": -2.0373624266058017,
    "random_rewards": -0.8726898117081002,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0392795500450545,
    "equal_rewards": -2.0086770429090706,
    "random_rewards": -1.0497812269590496,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0196796889234996,
    "equal_rewards": -2.0236915996316753,
    "random_rewards": -1.1929691078630809,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0471869961267783,
    "equal_rewards": -2.0194405175322965,
    "random_rewards": -2.0830317355818657,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0443596331169633,
    "equal_rewards": -2.0363745652834706,
    "random_rewards": -1.3540088367831482,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9841089574278614,
    "equal_rewards": -2.0446122101051754,
    "random_rewards": -1.8161849711755875,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.027018852576797,
    "equal_rewards": -2.0446422891075935,
    "random_rewards": -2.102629564321876,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.030921683577376,
    "equal_rewards": -2.022095591169322,
    "random_rewards": -1.7859471101742503,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0168694783514365,
    "equal_rewards": -2.034471097162524,
    "random_rewards": -1.6304234233646573,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0146005583353372,
    "equal_rewards": -2.034796350844811,
    "random_rewards": -1.9515780393483406,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0453735304874803,
    "equal_rewards": -2.065842297068595,
    "random_rewards": -3.018262508931281,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0132213572266937,
    "equal_rewards": -2.0474807956801135,
    "random_rewards": -1.221713075111948,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0395124683228483,
    "equal_rewards": -2.0078852510452516,
    "random_rewards": -1.7963172227119504,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.023353895267298,
    "equal_rewards": -2.0483741476092345,
    "random_rewards": -2.5320858857684896,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0784917056017633,
    "equal_rewards": -2.050565561459762,
    "random_rewards": -1.94440960319145,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.027045742804637,
    "equal_rewards": -2.0455719412690603,
    "random_rewards": -2.3955667986790097,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.979095173343417,
    "equal_rewards": -2.0214147227703387,
    "random_rewards": -2.9511912070238164,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.030786333346496,
    "equal_rewards": -2.0098823541034436,
    "random_rewards": -2.2130311886143117,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0168780441998124,
    "equal_rewards": -2.039959469662308,
    "random_rewards": -1.5294745611269218,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.050293157599172,
    "equal_rewards": -2.045047272696634,
    "random_rewards": -1.0557074199324754,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.023254184490521,
    "equal_rewards": -2.0289444523445446,
    "random_rewards": -2.225495764330136,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9851571626589115,
    "equal_rewards": -2.0297481802767003,
    "random_rewards": -1.7698415675548755,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9967887478762123,
    "equal_rewards": -2.0549810508492037,
    "random_rewards": -1.376432825151199,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.065872450714602,
    "equal_rewards": -2.0407786787155358,
    "random_rewards": -1.4724395225551257,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.045329213183091,
    "equal_rewards": -2.066724061081693,
    "random_rewards": -2.2745161969803402,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0328496815953074,
    "equal_rewards": -2.0366134862913317,
    "random_rewards": -1.8166816847971416,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.994692311090628,
    "equal_rewards": -2.036545991261884,
    "random_rewards": -2.211503036124724,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0515937922715173,
    "equal_rewards": -2.037951190155884,
    "random_rewards": -1.5163230405248083,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.029981926251522,
    "equal_rewards": -2.0090394556839732,
    "random_rewards": -1.7569005142637057,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0297186452218003,
    "equal_rewards": -1.996479471101126,
    "random_rewards": -1.9192928492618928,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9990842610002995,
    "equal_rewards": -2.064380954363144,
    "random_rewards": -0.7540038885490433,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0361766125390997,
    "equal_rewards": -2.041864140018907,
    "random_rewards": -1.051634817117053,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9854606981082301,
    "equal_rewards": -2.0307350987968396,
    "random_rewards": -2.3698776737680483,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0192528288977165,
    "equal_rewards": -2.047765081278358,
    "random_rewards": -2.2764156444397727,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.067171343777806,
    "equal_rewards": -2.0271273927162916,
    "random_rewards": -1.4658049901519155,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.032997326286423,
    "equal_rewards": -2.047299181379848,
    "random_rewards": -2.0754797131366622,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.026353967131333,
    "equal_rewards": -2.0347503114318837,
    "random_rewards": -1.9631582866388202,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0459478539089897,
    "equal_rewards": -2.0252698329914622,
    "random_rewards": -1.3373489198611646,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0134996545197303,
    "equal_rewards": -2.0662170405428,
    "random_rewards": -1.6505667338503276,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.022277268813613,
    "equal_rewards": -2.0472028790001517,
    "random_rewards": -1.6507898727748318,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.044514549656206,
    "equal_rewards": -2.0126022745922247,
    "random_rewards": -1.3071408636974295,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0162222146730433,
    "equal_rewards": -2.037067022807114,
    "random_rewards": -1.6056209531219503,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0217096956838665,
    "equal_rewards": -2.058900065490826,
    "random_rewards": -1.8183193298123976,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0141221307393646,
    "equal_rewards": -2.062415524126281,
    "random_rewards": -1.5386554011342326,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0312912514595984,
    "equal_rewards": -2.0262818801581965,
    "random_rewards": -2.247325991150198,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000687990532171,
    "equal_rewards": -2.02074718554744,
    "random_rewards": -1.4508725941505523,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0384277069265457,
    "equal_rewards": -2.0035396782543735,
    "random_rewards": -1.4786462644394527,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0077735826240626,
    "equal_rewards": -2.042697356192228,
    "random_rewards": -1.1954870262873178,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0318359687055256,
    "equal_rewards": -2.0193884032243288,
    "random_rewards": -2.0570255347998754,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.030034711185496,
    "equal_rewards": -2.0565407355280003,
    "random_rewards": -1.8071046822576582,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0543394395208474,
    "equal_rewards": -2.0353429947035013,
    "random_rewards": -1.337265192041838,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0118866975006204,
    "equal_rewards": -2.0341357937636837,
    "random_rewards": -1.9140433339389449,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9758907333755833,
    "equal_rewards": -2.02068425933702,
    "random_rewards": -1.7536227008863168,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0115339917885304,
    "equal_rewards": -2.0401070032406703,
    "random_rewards": -2.0995166929056457,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.036079956054058,
    "equal_rewards": -2.0209173366275874,
    "random_rewards": -0.883710334979055,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0032776437245006,
    "equal_rewards": -2.0678171265024874,
    "random_rewards": -2.593896344941542,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016642224418596,
    "equal_rewards": -2.011542359540907,
    "random_rewards": -0.8699376371964551,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9648212674119754,
    "equal_rewards": -2.0073458803103406,
    "random_rewards": -2.6583582554198575,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0433998402816953,
    "equal_rewards": -2.00406941888529,
    "random_rewards": -1.0217466883811777,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.03347547356549,
    "equal_rewards": -2.0014252323539967,
    "random_rewards": -0.8720344898771377,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9871742424404915,
    "equal_rewards": -2.046696877376098,
    "random_rewards": -1.6531598865166104,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.037290392096048,
    "equal_rewards": -2.028255556230133,
    "random_rewards": -0.8713718928409858,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007602113096944,
    "equal_rewards": -2.0031014985975086,
    "random_rewards": -1.5779579377112105,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0230701036471155,
    "equal_rewards": -2.044079593880381,
    "random_rewards": -2.2548354913188433,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0414482640793086,
    "equal_rewards": -2.0246756601358977,
    "random_rewards": -1.605437167909626,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9989837814977065,
    "equal_rewards": -2.0492970498754084,
    "random_rewards": -2.2653085723037125,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0395876465358715,
    "equal_rewards": -2.028444882293965,
    "random_rewards": -1.1887951485673733,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0154144761742177,
    "equal_rewards": -2.040329365506925,
    "random_rewards": -1.2014355507250687,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0126464201817695,
    "equal_rewards": -2.0357826185057175,
    "random_rewards": -2.054975900677613,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.062895125659809,
    "equal_rewards": -2.0215558005405025,
    "random_rewards": -1.797400116141639,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0587424006756563,
    "equal_rewards": -2.039643249655401,
    "random_rewards": -1.6571417718610064,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.019229457674169,
    "equal_rewards": -2.062573793092033,
    "random_rewards": -1.62976244393314,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0451098912884085,
    "equal_rewards": -2.0202085258434015,
    "random_rewards": -2.501245614611989,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0384740997156543,
    "equal_rewards": -2.019582537007082,
    "random_rewards": -1.6244993332430275,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.005566555602444,
    "equal_rewards": -2.055783625549479,
    "random_rewards": -1.3087030400698147,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.019680763748895,
    "equal_rewards": -2.050124637775305,
    "random_rewards": -2.1004146163987176,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.038547576966415,
    "equal_rewards": -2.020648796233833,
    "random_rewards": -1.046727916510957,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9892485396437,
    "equal_rewards": -2.0315737504118134,
    "random_rewards": -1.4500929012876949,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.999098419440658,
    "equal_rewards": -2.0572117035650264,
    "random_rewards": -1.2397278877855675,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0456840916769354,
    "equal_rewards": -2.0650119589332117,
    "random_rewards": -2.099160161017933,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0194437610874068,
    "equal_rewards": -2.05689528792907,
    "random_rewards": -2.2564830025944453,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9985065232103152,
    "equal_rewards": -2.0160626483355126,
    "random_rewards": -2.220063145647271,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0223086020438963,
    "equal_rewards": -2.0099637722378976,
    "random_rewards": -1.613225560981192,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0557148931882008,
    "equal_rewards": -2.018795412133299,
    "random_rewards": -1.0293752410444477,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.035225800307536,
    "equal_rewards": -1.9997183543649437,
    "random_rewards": -2.3612856339641732,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9977298481951344,
    "equal_rewards": -2.020246782197877,
    "random_rewards": -2.353722406445507,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.99149667713404,
    "equal_rewards": -2.049664193936791,
    "random_rewards": -2.2561010872726524,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0369793407149466,
    "equal_rewards": -2.0498455306367402,
    "random_rewards": -1.6648566220496557,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9903254824476124,
    "equal_rewards": -2.0087379575699775,
    "random_rewards": -2.5282921206648203,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9807368682297881,
    "equal_rewards": -2.033619685207099,
    "random_rewards": -0.7373454453724493,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.024841189060834,
    "equal_rewards": -2.0359230367639305,
    "random_rewards": -1.4779697142518713,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0292012292530184,
    "equal_rewards": -2.0132885931779643,
    "random_rewards": -1.7476548784391683,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0279709671374184,
    "equal_rewards": -2.0546618840947404,
    "random_rewards": -1.030394393490234,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.041751929298288,
    "equal_rewards": -2.0314155041671764,
    "random_rewards": -1.9100763794877254,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0058812238689443,
    "equal_rewards": -2.0266026973214784,
    "random_rewards": -1.91413341276289,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0035587729600173,
    "equal_rewards": -2.0586988068527337,
    "random_rewards": -2.1191478872335834,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0434187726010338,
    "equal_rewards": -2.0184051832293273,
    "random_rewards": -2.4987371312784776,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0289062059064444,
    "equal_rewards": -1.9979049916930713,
    "random_rewards": -2.210687208858396,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.005015607913875,
    "equal_rewards": -2.065561293141654,
    "random_rewards": -1.3625333258993515,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.041108663220064,
    "equal_rewards": -2.0280833244564347,
    "random_rewards": -2.2259451122082816,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.993103255450639,
    "equal_rewards": -2.022331646399727,
    "random_rewards": -2.4027021509520528,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0244195124622277,
    "equal_rewards": -2.0118959832417938,
    "random_rewards": -1.7710916608328966,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0247166719621728,
    "equal_rewards": -2.0553588100250355,
    "random_rewards": -2.5499660204425636,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0520546068876824,
    "equal_rewards": -2.033050260073294,
    "random_rewards": -2.5313496890684783,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0374762116517746,
    "equal_rewards": -2.0591599678315045,
    "random_rewards": -1.2267803748294968,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007831021505471,
    "equal_rewards": -2.0577953058772063,
    "random_rewards": -1.8151533304011345,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0104035249373173,
    "equal_rewards": -2.0393277358686377,
    "random_rewards": -0.5902987875620949,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0352939972231696,
    "equal_rewards": -2.024875168007904,
    "random_rewards": -1.3385511969826678,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0342586046388265,
    "equal_rewards": -2.021640943281429,
    "random_rewards": -2.062740942335257,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.048693664995364,
    "equal_rewards": -2.0231271670237967,
    "random_rewards": -1.794898923688801,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0084954494655967,
    "equal_rewards": -2.061721682709647,
    "random_rewards": -1.5090417624767956,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.001816840000573,
    "equal_rewards": -2.0444044389504583,
    "random_rewards": -2.2357699653544927,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0187989670085997,
    "equal_rewards": -2.041885657428752,
    "random_rewards": -1.0679493247096827,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.055427572424195,
    "equal_rewards": -2.042721868349044,
    "random_rewards": -1.1874768322976643,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0273943846992735,
    "equal_rewards": -2.04399809797981,
    "random_rewards": -2.6886293803834205,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0407159018369847,
    "equal_rewards": -2.0255539909020372,
    "random_rewards": -1.7741653328489315,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.017222937834205,
    "equal_rewards": -2.0604212949490135,
    "random_rewards": -1.6509279499352536,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0474212544568258,
    "equal_rewards": -2.0150669032363506,
    "random_rewards": -2.064773730747979,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0129733530710046,
    "equal_rewards": -2.037936566411549,
    "random_rewards": -1.6374102746472872,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.062558154832176,
    "equal_rewards": -2.0351189193391774,
    "random_rewards": -1.049994748554479,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0263003121223004,
    "equal_rewards": -2.067035860613499,
    "random_rewards": -1.066206209462849,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0100380013631316,
    "equal_rewards": -2.0560727339816887,
    "random_rewards": -1.6855856835760554,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.063022755966492,
    "equal_rewards": -2.027854147928293,
    "random_rewards": -2.3799284387789967,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.031656110376379,
    "equal_rewards": -2.01079384063244,
    "random_rewards": -1.305366963453209,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0071331051640717,
    "equal_rewards": -2.0226469809063117,
    "random_rewards": -1.0495839435461447,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9831916229505517,
    "equal_rewards": -2.042906777581284,
    "random_rewards": -1.7587618603109973,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0140051759491953,
    "equal_rewards": -2.044701285377327,
    "random_rewards": -1.9524906871932801,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0306388033379053,
    "equal_rewards": -1.998605557164999,
    "random_rewards": -1.9239281141384543,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0140368765109535,
    "equal_rewards": -2.040571672031839,
    "random_rewards": -1.7553472764559217,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0368936484095355,
    "equal_rewards": -2.024107530153632,
    "random_rewards": -1.2113340842375493,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0027065400092043,
    "equal_rewards": -2.0355454258672117,
    "random_rewards": -1.3010251964628803,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0395462481185023,
    "equal_rewards": -2.038121511470734,
    "random_rewards": -1.7740695023689526,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0132494542405714,
    "equal_rewards": -2.0806717117492637,
    "random_rewards": -1.5344543366262866,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0513700175724248,
    "equal_rewards": -2.029629310135798,
    "random_rewards": -1.1882771237211176,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0294568912573654,
    "equal_rewards": -1.9966976682827915,
    "random_rewards": -1.6012714634628185,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.027721879903625,
    "equal_rewards": -2.0562165131013117,
    "random_rewards": -1.3403477643103037,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0240954172110546,
    "equal_rewards": -2.061405394824708,
    "random_rewards": -1.649292112627885,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0289013692662543,
    "equal_rewards": -2.049107839099535,
    "random_rewards": -1.6327047436478495,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0138198500540456,
    "equal_rewards": -2.007350861095389,
    "random_rewards": -1.57989659376725,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010021963308814,
    "equal_rewards": -2.0329177458556167,
    "random_rewards": -1.7831086267497118,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0593488307592027,
    "equal_rewards": -2.040658997076525,
    "random_rewards": -2.1122360395666266,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0181297239367955,
    "equal_rewards": -2.063739526331566,
    "random_rewards": -2.249371274687791,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.040818522714701,
    "equal_rewards": -2.02557809386653,
    "random_rewards": -1.1606985849091322,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0532448524457436,
    "equal_rewards": -2.03774696568719,
    "random_rewards": -1.7656047693822046,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0324926200660576,
    "equal_rewards": -2.0611529815006397,
    "random_rewards": -2.4138598857928244,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.044391924164801,
    "equal_rewards": -2.026246841877491,
    "random_rewards": -1.9296293028426608,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0593664451497746,
    "equal_rewards": -2.033919726449816,
    "random_rewards": -1.344899926361602,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.024370384278045,
    "equal_rewards": -2.0532090111499497,
    "random_rewards": -1.4921819671792198,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.02479639447282,
    "equal_rewards": -2.0596270042436906,
    "random_rewards": -2.2455023222040857,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.036281999834855,
    "equal_rewards": -2.0291757500870506,
    "random_rewards": -2.8159352651346836,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0128781962018767,
    "equal_rewards": -2.0657090995726763,
    "random_rewards": -0.9001352777158104,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.035850193301546,
    "equal_rewards": -2.022933112043529,
    "random_rewards": -1.791397482210675,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0413686522046044,
    "equal_rewards": -2.019367249973401,
    "random_rewards": -1.905173944015211,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.037126327410869,
    "equal_rewards": -2.027989393906388,
    "random_rewards": -2.2071934579241215,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9834992433997058,
    "equal_rewards": -2.048365682205458,
    "random_rewards": -1.1753806375316451,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0394678593656193,
    "equal_rewards": -2.0506510558789124,
    "random_rewards": -1.673625442692878,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9984684867349432,
    "equal_rewards": -2.056704402014077,
    "random_rewards": -1.7808187885895963,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0657457846964844,
    "equal_rewards": -2.0377042114873154,
    "random_rewards": -2.11112537920974,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0111053977747653,
    "equal_rewards": -2.0558683370573263,
    "random_rewards": -2.0972683627218793,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0105571069563704,
    "equal_rewards": -2.016290538823685,
    "random_rewards": -1.944159030449777,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9938517984172361,
    "equal_rewards": -2.0392189534557605,
    "random_rewards": -1.6782010903303246,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0622843234478734,
    "equal_rewards": -2.0374024053857798,
    "random_rewards": -1.7881230151380059,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.047327420659577,
    "equal_rewards": -2.0690630080358936,
    "random_rewards": -1.634716983635621,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0591667409914765,
    "equal_rewards": -2.035006179068092,
    "random_rewards": -1.941194552996778,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9995390680130634,
    "equal_rewards": -2.0342345098137407,
    "random_rewards": -2.9843459509782027,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.043150874195579,
    "equal_rewards": -2.024090953318831,
    "random_rewards": -2.1018522264264563,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.022134026595016,
    "equal_rewards": -2.042111672804722,
    "random_rewards": -1.6271086776517778,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9924287482447154,
    "equal_rewards": -2.0552905616874138,
    "random_rewards": -2.3961207455751112,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0185712093183477,
    "equal_rewards": -2.05104316777265,
    "random_rewards": -1.1938635769630068,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.022156492105841,
    "equal_rewards": -2.0437401035141045,
    "random_rewards": -1.0544354257613637,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0499297978169944,
    "equal_rewards": -2.034590761191004,
    "random_rewards": -1.763395573814091,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0097270813796735,
    "equal_rewards": -2.067589859079537,
    "random_rewards": -1.9360771943606863,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.046427498303639,
    "equal_rewards": -2.031141497058376,
    "random_rewards": -1.8030308058997473,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0544983650214617,
    "equal_rewards": -2.0385624561196884,
    "random_rewards": -1.1989287912093616,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0114658379825134,
    "equal_rewards": -2.067108286390467,
    "random_rewards": -2.2769849032673672,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.047901217964826,
    "equal_rewards": -2.02488943037047,
    "random_rewards": -1.909493782299866,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0033937828058983,
    "equal_rewards": -2.033099709940299,
    "random_rewards": -1.6655886744247064,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.035009992769659,
    "equal_rewards": -1.9984598059777627,
    "random_rewards": -1.8829377310204765,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007627195320273,
    "equal_rewards": -2.0675675503008923,
    "random_rewards": -2.1256138263968616,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0116036449177908,
    "equal_rewards": -2.051433583678699,
    "random_rewards": -1.3455835752421978,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9968324055570839,
    "equal_rewards": -2.0496602810264557,
    "random_rewards": -2.1289394499202885,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.043898433423525,
    "equal_rewards": -2.028634629891264,
    "random_rewards": -2.0946416983923166,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0516786472321176,
    "equal_rewards": -2.0394987343501834,
    "random_rewards": -1.4866022175633598,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0418702075761552,
    "equal_rewards": -2.0319433682251904,
    "random_rewards": -1.9628361843309245,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0166130421495043,
    "equal_rewards": -2.0646871934486732,
    "random_rewards": -2.274063952203149,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0420113375446127,
    "equal_rewards": -2.061305696468911,
    "random_rewards": -2.5680683394394004,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.036375504829401,
    "equal_rewards": -2.0474374072140082,
    "random_rewards": -1.5266677241276665,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0071753195527995,
    "equal_rewards": -2.0359958342435696,
    "random_rewards": -1.9266505984591191,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0638049343551734,
    "equal_rewards": -2.04131208410983,
    "random_rewards": -1.3378939972158381,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.020346179601858,
    "equal_rewards": -2.0274174807212324,
    "random_rewards": -2.253407357503335,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9992129042839886,
    "equal_rewards": -2.026090695706159,
    "random_rewards": -1.7412047622488205,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0441612321826677,
    "equal_rewards": -2.0388901074187875,
    "random_rewards": -1.5037333264517898,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.030919507646569,
    "equal_rewards": -2.055872981861704,
    "random_rewards": -1.6665305204882346,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0461077890033685,
    "equal_rewards": -2.0284107048041857,
    "random_rewards": -2.0522942601611303,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.012586491612166,
    "equal_rewards": -2.0583238210086336,
    "random_rewards": -1.9614381831442098,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0255578336689855,
    "equal_rewards": -2.066719524107297,
    "random_rewards": -1.9280295795389755,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.053622691200839,
    "equal_rewards": -2.019996020994271,
    "random_rewards": -1.6520189528398872,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0248582678019877,
    "equal_rewards": -2.041355903747985,
    "random_rewards": -1.3738984547491355,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.008883907565829,
    "equal_rewards": -2.061559315037938,
    "random_rewards": -1.3415611225125654,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016547607455265,
    "equal_rewards": -2.0537425243369682,
    "random_rewards": -1.6644784222250502,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0395739467643907,
    "equal_rewards": -2.0611975775513454,
    "random_rewards": -1.5158026305181274,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.05827871624783,
    "equal_rewards": -2.039024110106626,
    "random_rewards": -1.9446031532463097,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0297827431610465,
    "equal_rewards": -2.058318031955732,
    "random_rewards": -1.9655481463022195,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.058216687001875,
    "equal_rewards": -2.0212286848126375,
    "random_rewards": -2.522432908239888,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0316201001166996,
    "equal_rewards": -2.0401269508488817,
    "random_rewards": -2.110768670725144,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0377809748631064,
    "equal_rewards": -2.0225426923995213,
    "random_rewards": -2.953335516254043,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9998650910769242,
    "equal_rewards": -2.042152142678841,
    "random_rewards": -1.1804323440711086,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0115164615577394,
    "equal_rewards": -2.0399179813155843,
    "random_rewards": -2.076415103722823,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0540410176181427,
    "equal_rewards": -2.035142760355228,
    "random_rewards": -2.2168472302720335,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013377970275974,
    "equal_rewards": -2.0663629225411286,
    "random_rewards": -1.2307584337235173,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.051080831844434,
    "equal_rewards": -2.0352066312115404,
    "random_rewards": -1.9472305676918098,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.008487899061604,
    "equal_rewards": -2.066430948322733,
    "random_rewards": -2.137287883895346,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0519320993139263,
    "equal_rewards": -2.039628350516311,
    "random_rewards": -1.1996422036756766,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0350018571786204,
    "equal_rewards": -2.0216126652103243,
    "random_rewards": -1.330482828264948,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9854001929428198,
    "equal_rewards": -2.038310818553841,
    "random_rewards": -1.1629914148972542,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.04219693302982,
    "equal_rewards": -2.029494987994636,
    "random_rewards": -2.2374351516547337,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0041562106152897,
    "equal_rewards": -2.0452240723882706,
    "random_rewards": -1.2046706961854108,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0497166746339337,
    "equal_rewards": -2.0178444453392568,
    "random_rewards": -1.4941532666561756,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011580979434968,
    "equal_rewards": -2.0258111858060763,
    "random_rewards": -1.4405794912261256,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.024671895763767,
    "equal_rewards": -2.046249881091851,
    "random_rewards": -1.3353892915927572,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0148785190081098,
    "equal_rewards": -2.0729164943388483,
    "random_rewards": -2.4172420202275715,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.029269405339298,
    "equal_rewards": -2.035986928778041,
    "random_rewards": -1.6755907104670877,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.002423943434295,
    "equal_rewards": -2.0270051828177027,
    "random_rewards": -1.7451723190420299,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0242269430851456,
    "equal_rewards": -2.04069886865924,
    "random_rewards": -0.7451470125077526,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.018578321369695,
    "equal_rewards": -2.0339559578082533,
    "random_rewards": -2.2350928124575007,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.027554201020831,
    "equal_rewards": -2.050854297342835,
    "random_rewards": -1.6620322005669146,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013410086604788,
    "equal_rewards": -2.071474882350466,
    "random_rewards": -2.153748575724277,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0663547693952085,
    "equal_rewards": -2.038511783525783,
    "random_rewards": -1.6237194590817894,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0364994366774667,
    "equal_rewards": -2.0493313423769,
    "random_rewards": -2.5335323680744164,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9986167804646648,
    "equal_rewards": -2.056150026965156,
    "random_rewards": -1.9609630592714216,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0720495840821482,
    "equal_rewards": -2.041289119610565,
    "random_rewards": -1.4774725310521697,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0235484743989036,
    "equal_rewards": -2.0459656360829577,
    "random_rewards": -1.7669055301574315,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0049461627645755,
    "equal_rewards": -2.0212954171455055,
    "random_rewards": -1.7643404268169596,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.044307744234187,
    "equal_rewards": -2.026470181558294,
    "random_rewards": -2.5292564550336527,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0168939971757043,
    "equal_rewards": -2.064763265514376,
    "random_rewards": -1.0719042677078676,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0079159712287935,
    "equal_rewards": -2.045228378364464,
    "random_rewards": -2.08019340061198,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9911849548836642,
    "equal_rewards": -2.0558735130082453,
    "random_rewards": -1.3938955294162365,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.051940859673112,
    "equal_rewards": -2.0367254312269045,
    "random_rewards": -2.26544082436883,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0103778629397895,
    "equal_rewards": -2.045148476881801,
    "random_rewards": -2.672091257048155,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9952352262974038,
    "equal_rewards": -2.0483107320081504,
    "random_rewards": -2.56239635191621,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.050428001546992,
    "equal_rewards": -2.0301823903797156,
    "random_rewards": -1.9593445655038506,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0079145590068483,
    "equal_rewards": -2.051295319111924,
    "random_rewards": -2.701369892660816,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021393185231107,
    "equal_rewards": -2.041387809884408,
    "random_rewards": -1.0677759169392187,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.009910443828293,
    "equal_rewards": -2.0304731219896404,
    "random_rewards": -1.637220196843141,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0112186675368164,
    "equal_rewards": -2.0619427358584077,
    "random_rewards": -1.0553811592909692,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0383502714983237,
    "equal_rewards": -2.03115415697195,
    "random_rewards": -1.5092408339721857,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0114595371412274,
    "equal_rewards": -2.0464822807558027,
    "random_rewards": -1.7891659633441406,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0306884654979536,
    "equal_rewards": -2.021772955769709,
    "random_rewards": -1.0436501468607704,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.012534129729638,
    "equal_rewards": -2.0656837929505327,
    "random_rewards": -1.7852107021134636,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0124212958278083,
    "equal_rewards": -2.063092202248414,
    "random_rewards": -1.9407961455066505,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.001731134818637,
    "equal_rewards": -2.0462135405561845,
    "random_rewards": -1.5040679853920418,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.026672358967811,
    "equal_rewards": -2.006434545725858,
    "random_rewards": -2.0237992784027017,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0468239850681686,
    "equal_rewards": -2.0068659020345536,
    "random_rewards": -2.073957609059168,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0242753587535285,
    "equal_rewards": -2.049264542399851,
    "random_rewards": -2.854020347467971,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0298752814100345,
    "equal_rewards": -2.05648642124362,
    "random_rewards": -2.1350975680622435,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0234455670580207,
    "equal_rewards": -2.052272472556739,
    "random_rewards": -2.1204442185988146,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.006659825919187,
    "equal_rewards": -2.044200131551397,
    "random_rewards": -2.7070508336851753,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0152655125585275,
    "equal_rewards": -2.038394090341821,
    "random_rewards": -1.9402846609445996,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0104733188515698,
    "equal_rewards": -2.065646674276375,
    "random_rewards": -1.9883797479141714,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.019125255915294,
    "equal_rewards": -2.047941949534235,
    "random_rewards": -1.6121363267303783,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.036231182876454,
    "equal_rewards": -2.0289571392238797,
    "random_rewards": -1.9356089496893434,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0182410425176416,
    "equal_rewards": -2.0612203202166532,
    "random_rewards": -1.9684986103669722,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.060856149228511,
    "equal_rewards": -2.0328332346190865,
    "random_rewards": -1.0489798695766357,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0560049342444566,
    "equal_rewards": -2.0320336801871397,
    "random_rewards": -2.6763370421976966,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.012375355206116,
    "equal_rewards": -2.0288682719405444,
    "random_rewards": -1.4746756621164636,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0318963229550935,
    "equal_rewards": -2.0569457735537244,
    "random_rewards": -2.5804569776113286,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.015767752322787,
    "equal_rewards": -2.061605838648835,
    "random_rewards": -0.905095246236074,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016496393012601,
    "equal_rewards": -2.0671218254034516,
    "random_rewards": -2.427364309537399,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.031143604151866,
    "equal_rewards": -2.0369093053867005,
    "random_rewards": -1.1865507848601782,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0276559461144235,
    "equal_rewards": -2.020509227218729,
    "random_rewards": -2.359341697267983,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0337148599463983,
    "equal_rewards": -2.05553606328421,
    "random_rewards": -2.8653442115418253,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.009780172998171,
    "equal_rewards": -2.0471891736163275,
    "random_rewards": -1.4836461046894298,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0077312861549323,
    "equal_rewards": -2.024172795075854,
    "random_rewards": -2.5242351233253433,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0275593591627405,
    "equal_rewards": -2.054329140497115,
    "random_rewards": -2.8636568197217103,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.026543593295517,
    "equal_rewards": -2.0469473527921647,
    "random_rewards": -1.0455213968158437,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.02758372047183,
    "equal_rewards": -2.038938486037486,
    "random_rewards": -1.4652183721098835,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9977540705521577,
    "equal_rewards": -2.0602120116643183,
    "random_rewards": -1.0536151450264437,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.063770153089301,
    "equal_rewards": -2.026888592650373,
    "random_rewards": -1.9509325664185657,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.029293092687195,
    "equal_rewards": -2.0560278408608323,
    "random_rewards": -0.5945982081187098,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0529521388232768,
    "equal_rewards": -2.037032339703474,
    "random_rewards": -2.392915829686764,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0263569487566944,
    "equal_rewards": -2.0569316921843988,
    "random_rewards": -0.7519147957762988,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016434254980966,
    "equal_rewards": -2.045033656324764,
    "random_rewards": -1.0605030065191987,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0150183875091447,
    "equal_rewards": -2.044634533830278,
    "random_rewards": -1.8373995028089067,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.030265261635934,
    "equal_rewards": -2.007799574383625,
    "random_rewards": -2.6387920481179368,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0478122222309487,
    "equal_rewards": -2.0226030837876117,
    "random_rewards": -2.498443305617662,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0419507005090285,
    "equal_rewards": -2.0635699907186216,
    "random_rewards": -2.267169678258298,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0354603772547066,
    "equal_rewards": -2.06197238308553,
    "random_rewards": -1.8119470285977637,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0477740861938707,
    "equal_rewards": -2.0351370890117937,
    "random_rewards": -2.111399351089013,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007793350760304,
    "equal_rewards": -2.0583239016921304,
    "random_rewards": -2.1022354911591528,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0144599010102127,
    "equal_rewards": -2.0431045545816477,
    "random_rewards": -1.9795682575502143,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.014204276985479,
    "equal_rewards": -2.0243253206866694,
    "random_rewards": -1.8974211079969074,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.009452545274573,
    "equal_rewards": -2.0286378123661652,
    "random_rewards": -0.9132920046333329,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0339024302315765,
    "equal_rewards": -2.0504124119463096,
    "random_rewards": -2.2548139180008424,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0323489251657407,
    "equal_rewards": -2.0554608363836127,
    "random_rewards": -2.2662391646557025,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.015078064408761,
    "equal_rewards": -2.0610579419474826,
    "random_rewards": -1.9811806850181983,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0473903024088393,
    "equal_rewards": -2.0722582544115546,
    "random_rewards": -1.7965950226691612,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0297059659418286,
    "equal_rewards": -2.0498035128449037,
    "random_rewards": -1.680428946343376,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0516403202100206,
    "equal_rewards": -2.0243363986073835,
    "random_rewards": -2.1026894302090624,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0162971609306855,
    "equal_rewards": -2.046806430129434,
    "random_rewards": -2.388941312824155,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0313872517606795,
    "equal_rewards": -2.0559101310336083,
    "random_rewards": -2.69293414472346,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.034977871839354,
    "equal_rewards": -2.063762344975402,
    "random_rewards": -1.6222451846346033,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.030549882869964,
    "equal_rewards": -2.0449482196724187,
    "random_rewards": -2.2158944063540207,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0578176482857047,
    "equal_rewards": -2.0275277163488745,
    "random_rewards": -1.790677028891307,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.044306433286823,
    "equal_rewards": -2.060622256784577,
    "random_rewards": -1.7904818049581273,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.012739984227823,
    "equal_rewards": -2.0702438788058597,
    "random_rewards": -2.1009169187729837,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0279450776445542,
    "equal_rewards": -2.045685604315918,
    "random_rewards": -1.0775178503140153,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.029148688828706,
    "equal_rewards": -2.013890512348052,
    "random_rewards": -1.761192815588842,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0141569771248204,
    "equal_rewards": -2.0623167258988406,
    "random_rewards": -1.3660475530831446,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0157090362791736,
    "equal_rewards": -2.0528001753339473,
    "random_rewards": -1.671873331883881,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0466100769486366,
    "equal_rewards": -2.0656420880481927,
    "random_rewards": -2.5759977882628826,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0186653211794434,
    "equal_rewards": -2.060971236406261,
    "random_rewards": -2.4101945081648815,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9990293105674766,
    "equal_rewards": -2.054464521795954,
    "random_rewards": -1.9383664829622607,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.044025539243388,
    "equal_rewards": -2.036996349742676,
    "random_rewards": -1.7640064751726472,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0341857679584,
    "equal_rewards": -2.050636453202829,
    "random_rewards": -1.8161827343894357,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0666780710982597,
    "equal_rewards": -2.025793211087559,
    "random_rewards": -2.0858329891615384,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021359351523433,
    "equal_rewards": -2.0693657234343146,
    "random_rewards": -1.6724187114615292,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.046079918160641,
    "equal_rewards": -2.025757078276278,
    "random_rewards": -2.9581848661441756,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0566360032824793,
    "equal_rewards": -2.03781678527468,
    "random_rewards": -1.8022574707436332,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.01248293280777,
    "equal_rewards": -2.0751576268326795,
    "random_rewards": -2.597358391461559,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0214088252103215,
    "equal_rewards": -2.0719845947912505,
    "random_rewards": -2.0022327693982818,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.024152458336933,
    "equal_rewards": -2.0440187479183822,
    "random_rewards": -2.3994612283800327,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9941389422214124,
    "equal_rewards": -2.0617314764559156,
    "random_rewards": -2.5604357489583345,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0542579383054798,
    "equal_rewards": -2.041672302600394,
    "random_rewards": -2.0894389862588225,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0709920056734346,
    "equal_rewards": -2.040655128582091,
    "random_rewards": -0.5979815741828898,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.039156502511359,
    "equal_rewards": -2.050201457271763,
    "random_rewards": -1.5109862139583203,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0203375873185796,
    "equal_rewards": -2.0110706102016995,
    "random_rewards": -1.3109335280653256,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9964207501300728,
    "equal_rewards": -2.0418209258046724,
    "random_rewards": -0.9042201606403596,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0517121839483856,
    "equal_rewards": -2.070969926040627,
    "random_rewards": -2.2589524586707608,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0278271978857503,
    "equal_rewards": -2.0852107728631886,
    "random_rewards": -2.60887821659144,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.029326190022336,
    "equal_rewards": -2.044979829390484,
    "random_rewards": -1.9206718436623114,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.040703466889692,
    "equal_rewards": -2.024513469246444,
    "random_rewards": -2.1032684166315687,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0303584146517695,
    "equal_rewards": -2.065228056222081,
    "random_rewards": -1.534273288370448,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0172511543794807,
    "equal_rewards": -2.0375657795599778,
    "random_rewards": -1.6698444485326653,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.045025514319846,
    "equal_rewards": -2.0068931046579603,
    "random_rewards": -1.619853027309099,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.048929276211157,
    "equal_rewards": -2.0436346651956594,
    "random_rewards": -2.246503973189421,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0354477178166377,
    "equal_rewards": -2.0586199951816284,
    "random_rewards": -1.0454595021714352,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0376381918837483,
    "equal_rewards": -2.062360500095469,
    "random_rewards": -2.073871403634048,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021326008664463,
    "equal_rewards": -2.0367343016102026,
    "random_rewards": -2.9873748997547795,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.987020837138798,
    "equal_rewards": -2.0544765867854076,
    "random_rewards": -2.1062935071265287,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.027358499834747,
    "equal_rewards": -2.0390379429622545,
    "random_rewards": -1.8187630926390437,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0253731172820206,
    "equal_rewards": -2.010284701348949,
    "random_rewards": -2.1905358703670608,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011267441564402,
    "equal_rewards": -2.0663133956608375,
    "random_rewards": -1.5195612702639612,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0395647093418265,
    "equal_rewards": -2.068018507743985,
    "random_rewards": -1.5367989974835927,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.06149339504681,
    "equal_rewards": -2.0471238429107848,
    "random_rewards": -1.622307716797933,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.026632968322951,
    "equal_rewards": -2.0675249099474025,
    "random_rewards": -1.9291285783120684,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.025491324864995,
    "equal_rewards": -2.029685954100385,
    "random_rewards": -0.8892460416760651,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0039776777495852,
    "equal_rewards": -2.0286428382638575,
    "random_rewards": -2.6673310001486477,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.033790090814323,
    "equal_rewards": -2.046196086965016,
    "random_rewards": -1.1851748267576925,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.061870851672273,
    "equal_rewards": -2.023423496899082,
    "random_rewards": -1.6336097074546754,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0178573161803004,
    "equal_rewards": -2.0634332898927985,
    "random_rewards": -1.7823777663340077,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.053074382412591,
    "equal_rewards": -2.0374799240622288,
    "random_rewards": -2.8371008362722545,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0430447056198546,
    "equal_rewards": -2.064518036363665,
    "random_rewards": -1.6684869921262637,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0671545302851877,
    "equal_rewards": -2.048469434966012,
    "random_rewards": -1.3754619113079594,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0169144431072987,
    "equal_rewards": -2.076809945333475,
    "random_rewards": -2.3250553993106746,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0190244451249497,
    "equal_rewards": -2.065061220569803,
    "random_rewards": -2.716264933874612,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0407973997215287,
    "equal_rewards": -2.0691129333189657,
    "random_rewards": -1.8156444996432537,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0383015071909614,
    "equal_rewards": -2.065132040120442,
    "random_rewards": -0.8917927170807762,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.068207204002061,
    "equal_rewards": -2.043124200517716,
    "random_rewards": -1.7870556664421757,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021234067664603,
    "equal_rewards": -2.0560064091749366,
    "random_rewards": -2.686396977018716,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9890555346175884,
    "equal_rewards": -2.050020058597219,
    "random_rewards": -2.0718207847853614,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.057164199964636,
    "equal_rewards": -2.026544368104363,
    "random_rewards": -1.465630485172285,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0358132038718364,
    "equal_rewards": -2.0233505555135403,
    "random_rewards": -1.3199664601873913,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.009720526382282,
    "equal_rewards": -2.0675253985980975,
    "random_rewards": -1.8595068242577666,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.04593757459039,
    "equal_rewards": -2.030558490724446,
    "random_rewards": -2.6743941097346364,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0372534511913782,
    "equal_rewards": -2.0242925811589583,
    "random_rewards": -2.2473477928542147,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.018833773665556,
    "equal_rewards": -2.0436468164474317,
    "random_rewards": -1.2263393874925763,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0157899657990255,
    "equal_rewards": -2.071197515157104,
    "random_rewards": -1.2185290307149257,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0225608176763417,
    "equal_rewards": -2.065885433895376,
    "random_rewards": -1.6703750702900737,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.034137772100226,
    "equal_rewards": -2.0427856177879016,
    "random_rewards": -1.7677867740490858,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.036116763682486,
    "equal_rewards": -2.031782077218533,
    "random_rewards": -1.9547022409453714,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0204663934817524,
    "equal_rewards": -2.0448884564950816,
    "random_rewards": -1.0512432198386166,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.998496132602681,
    "equal_rewards": -2.0516177884318463,
    "random_rewards": -1.4785637605143327,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0301100210440106,
    "equal_rewards": -2.0341355232251925,
    "random_rewards": -1.617746954283872,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9950553807967926,
    "equal_rewards": -2.0504670255968627,
    "random_rewards": -2.685796385238632,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0317517922647483,
    "equal_rewards": -2.0478051439455878,
    "random_rewards": -1.3455054155246853,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.023346628685193,
    "equal_rewards": -2.0519574507606713,
    "random_rewards": -1.67379894799368,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0690738744315302,
    "equal_rewards": -2.043688448481666,
    "random_rewards": -2.234366970986473,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0288517055276127,
    "equal_rewards": -2.040473719431238,
    "random_rewards": -1.2072903471639127,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9988185866588597,
    "equal_rewards": -2.0316374059104314,
    "random_rewards": -2.375407895971456,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0373282913753448,
    "equal_rewards": -2.0640897514694063,
    "random_rewards": -1.3659625612721276,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0296840800815197,
    "equal_rewards": -2.05441734986404,
    "random_rewards": -1.960344819884349,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0460872212337353,
    "equal_rewards": -2.0206984382319684,
    "random_rewards": -1.8044395126293515,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9849893776318563,
    "equal_rewards": -2.0521670442984443,
    "random_rewards": -2.4005943088728934,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0601754198074316,
    "equal_rewards": -2.051164100555022,
    "random_rewards": -1.3332355217386327,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0424654778327214,
    "equal_rewards": -2.0628894116219954,
    "random_rewards": -2.1114072013508673,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.024562888437318,
    "equal_rewards": -2.051806244055737,
    "random_rewards": -1.8067293365460166,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.017988696139022,
    "equal_rewards": -2.042830876768372,
    "random_rewards": -1.770798797926659,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.065860684903121,
    "equal_rewards": -2.0435778888157934,
    "random_rewards": -1.508878519914619,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0313512540835754,
    "equal_rewards": -2.047224439546863,
    "random_rewards": -1.964112844645426,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.00820702366819,
    "equal_rewards": -2.04102891484429,
    "random_rewards": -2.5397769148110356,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011469019552994,
    "equal_rewards": -2.052922491486384,
    "random_rewards": -1.3602673554568763,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.018590579304091,
    "equal_rewards": -2.0719146683354843,
    "random_rewards": -2.112548485826705,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.058547112330907,
    "equal_rewards": -2.0395870428698677,
    "random_rewards": -2.5491530391525274,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0348178638885113,
    "equal_rewards": -2.063471137495384,
    "random_rewards": -2.8763922935981854,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0139573383269065,
    "equal_rewards": -2.066563971333406,
    "random_rewards": -2.713861451191867,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.006796902749617,
    "equal_rewards": -2.0517383375343816,
    "random_rewards": -1.5143842575061846,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0347014776906516,
    "equal_rewards": -2.0294014693590157,
    "random_rewards": -2.516012244072619,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0631061999626272,
    "equal_rewards": -2.0378723001899255,
    "random_rewards": -1.9262358518589533,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0197317346264163,
    "equal_rewards": -2.0728307253360687,
    "random_rewards": -2.0088374916456977,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.050425602126506,
    "equal_rewards": -2.0296464306392656,
    "random_rewards": -1.4804558642024426,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0404613597145698,
    "equal_rewards": -2.0245605348631623,
    "random_rewards": -1.506500818084973,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0374820469258506,
    "equal_rewards": -2.0622053725712766,
    "random_rewards": -1.4871577253504342,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0199375468240612,
    "equal_rewards": -2.0703192187269672,
    "random_rewards": -2.0144514750054023,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0240071632409475,
    "equal_rewards": -2.048766535203751,
    "random_rewards": -2.407166659233866,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.040046280595533,
    "equal_rewards": -2.05933744520019,
    "random_rewards": -1.4887095878224585,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0374386559185247,
    "equal_rewards": -2.043183370149263,
    "random_rewards": -2.841480636012004,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9890511032291913,
    "equal_rewards": -2.0471561684922315,
    "random_rewards": -2.5606367077867573,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0110295416411716,
    "equal_rewards": -2.0668629094943527,
    "random_rewards": -1.3478222109697122,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.03621197139615,
    "equal_rewards": -2.026250097461894,
    "random_rewards": -2.254327772203634,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0080968296785784,
    "equal_rewards": -2.0610132997485255,
    "random_rewards": -1.3491221061786365,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0203787882901327,
    "equal_rewards": -2.035740064512657,
    "random_rewards": -1.4953945189385558,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9941197054524817,
    "equal_rewards": -2.051484768738491,
    "random_rewards": -1.9247826772502803,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0269275604881405,
    "equal_rewards": -2.0381108093402305,
    "random_rewards": -0.8745488882304469,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0402072975799403,
    "equal_rewards": -2.0212418014076126,
    "random_rewards": -2.367819483341177,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.008760283362921,
    "equal_rewards": -2.0741257372692967,
    "random_rewards": -1.6397541196994512,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.072689112573645,
    "equal_rewards": -2.0318173436657125,
    "random_rewards": -2.383216935250534,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.045056019984208,
    "equal_rewards": -2.0324751761059825,
    "random_rewards": -2.381520841660507,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0340844106855838,
    "equal_rewards": -2.060581277291142,
    "random_rewards": -1.9395000839014824,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0585259729427308,
    "equal_rewards": -2.0252689241736266,
    "random_rewards": -1.333776296416147,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.019217585005519,
    "equal_rewards": -2.0479085316639596,
    "random_rewards": -1.6617328326502399,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.031953655037475,
    "equal_rewards": -2.0585812685477154,
    "random_rewards": -1.6708616595281824,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.060717863439361,
    "equal_rewards": -2.021543123538265,
    "random_rewards": -1.953195323846065,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0029581368265315,
    "equal_rewards": -2.063322561423378,
    "random_rewards": -2.410003936365274,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0399568424541403,
    "equal_rewards": -2.0382572847037554,
    "random_rewards": -1.3350666969643061,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0149124493454877,
    "equal_rewards": -2.07266461081388,
    "random_rewards": -1.8070715164621876,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0402558060128166,
    "equal_rewards": -2.061760576681868,
    "random_rewards": -1.355537335841202,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.05196865428779,
    "equal_rewards": -2.0352827589338407,
    "random_rewards": -1.473090035671042,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9937434352422134,
    "equal_rewards": -2.05177771081388,
    "random_rewards": -2.5451400451078494,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0566028827849134,
    "equal_rewards": -2.0407980889968624,
    "random_rewards": -2.1031814801694697,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0556709438775176,
    "equal_rewards": -2.0317124295665767,
    "random_rewards": -1.4682093258243942,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9943142650902015,
    "equal_rewards": -2.0574176760467613,
    "random_rewards": -1.5414632425170647,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0268989167015126,
    "equal_rewards": -2.067780358598384,
    "random_rewards": -1.3543205048286877,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0351097100766014,
    "equal_rewards": -2.061643636470757,
    "random_rewards": -2.125882734739458,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.060751065647672,
    "equal_rewards": -2.025160866376703,
    "random_rewards": -0.5871971925227681,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.037622287915079,
    "equal_rewards": -2.02877530827272,
    "random_rewards": -1.788312290828924,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.064059513272167,
    "equal_rewards": -2.0288057848379366,
    "random_rewards": -1.3292209077617843,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010588643973971,
    "equal_rewards": -2.0714553199290853,
    "random_rewards": -1.7956597012417628,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.03635105538597,
    "equal_rewards": -2.0648360484778525,
    "random_rewards": -1.6382900270490413,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.058962294619498,
    "equal_rewards": -2.039681161640898,
    "random_rewards": -2.4025168797685,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0237759669938216,
    "equal_rewards": -2.0525340928991396,
    "random_rewards": -1.9644609332609724,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0130103703612203,
    "equal_rewards": -2.0660748518046717,
    "random_rewards": -2.010536079994222,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0391253156164098,
    "equal_rewards": -2.0606173461335464,
    "random_rewards": -1.1986379061886163,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.014359389619351,
    "equal_rewards": -2.074557047496983,
    "random_rewards": -1.8153219182868874,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0612336223848446,
    "equal_rewards": -2.0423486055799085,
    "random_rewards": -2.254945124470175,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.044150079879451,
    "equal_rewards": -2.0425954848837153,
    "random_rewards": -1.9616678355965724,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.035019407037034,
    "equal_rewards": -2.069964591307915,
    "random_rewards": -2.234030336057376,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0561427887090833,
    "equal_rewards": -2.040409928383821,
    "random_rewards": -2.3901303681912496,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0167126761915615,
    "equal_rewards": -2.069670923900021,
    "random_rewards": -2.572618411288951,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0074308175621276,
    "equal_rewards": -2.0629037412044617,
    "random_rewards": -1.7980803473707967,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.032932394864025,
    "equal_rewards": -2.048862641226547,
    "random_rewards": -2.383752227981599,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0364423531683884,
    "equal_rewards": -2.0136029453197164,
    "random_rewards": -1.896074198531418,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0519216930690063,
    "equal_rewards": -2.0213485482270483,
    "random_rewards": -1.3074678863013083,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0207707650577698,
    "equal_rewards": -2.0843119977523705,
    "random_rewards": -2.724424103273144,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0168300665112326,
    "equal_rewards": -2.0505869811423776,
    "random_rewards": -2.687742665074148,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0121646127902095,
    "equal_rewards": -2.029997189640101,
    "random_rewards": -1.2178268884887673,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9929693369992705,
    "equal_rewards": -2.0514510143096647,
    "random_rewards": -2.8675406151228806,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.033516279683539,
    "equal_rewards": -2.0601215991900648,
    "random_rewards": -2.261109072281778,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0169739894189815,
    "equal_rewards": -2.0581167344791798,
    "random_rewards": -1.4678260988866927,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0329998691605797,
    "equal_rewards": -2.0262097550529385,
    "random_rewards": -2.184008863312757,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.053125958712487,
    "equal_rewards": -2.0406321096874804,
    "random_rewards": -1.7776999881397182,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.015203537949583,
    "equal_rewards": -2.0613586802319483,
    "random_rewards": -2.2537726910239613,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0001206708859165,
    "equal_rewards": -2.053944794289849,
    "random_rewards": -1.6595654042484282,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.027448300472333,
    "equal_rewards": -2.0169197714805467,
    "random_rewards": -1.1658056916389374,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9883511984981228,
    "equal_rewards": -2.0310478300199817,
    "random_rewards": -2.2308584561399143,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0173870240054166,
    "equal_rewards": -2.0048060728149357,
    "random_rewards": -1.770676045753456,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.996403939139658,
    "equal_rewards": -2.0468333121343973,
    "random_rewards": -2.247533996997144,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.020331564731204,
    "equal_rewards": -2.0735759134473533,
    "random_rewards": -2.5638597031748946,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016756444130813,
    "equal_rewards": -2.0424007996516202,
    "random_rewards": -0.5902388568808857,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9812198189139145,
    "equal_rewards": -2.0373780234034453,
    "random_rewards": -1.6170513010857883,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0335343298757165,
    "equal_rewards": -2.020199997152206,
    "random_rewards": -2.0633191556526627,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9862479970652465,
    "equal_rewards": -2.015258216391403,
    "random_rewards": -1.9061125105324797,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.061177314726091,
    "equal_rewards": -2.022734325774989,
    "random_rewards": -1.3285094994006545,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0087828675933763,
    "equal_rewards": -2.071955469916448,
    "random_rewards": -1.9742911008312083,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0380450100129517,
    "equal_rewards": -2.022153306447056,
    "random_rewards": -1.0116480734768203,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.001801840401594,
    "equal_rewards": -2.0230626148203443,
    "random_rewards": -1.334321389546475,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.026264058239853,
    "equal_rewards": -2.0546901225749297,
    "random_rewards": -1.932251186070407,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0647823335078765,
    "equal_rewards": -2.03978019475458,
    "random_rewards": -1.777948999768396,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0145681929077126,
    "equal_rewards": -2.0523689604660067,
    "random_rewards": -1.5089387817235633,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0142831096424487,
    "equal_rewards": -2.040922001222574,
    "random_rewards": -2.077594445056838,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004885508177101,
    "equal_rewards": -2.07281738145243,
    "random_rewards": -1.6507219981906687,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0472547997492545,
    "equal_rewards": -2.028923883543743,
    "random_rewards": -1.7919214063326199,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.997791118266421,
    "equal_rewards": -2.03108718809524,
    "random_rewards": -0.8999613379209734,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.022994627152674,
    "equal_rewards": -2.043754636041256,
    "random_rewards": -1.6434794026715294,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0572925111424056,
    "equal_rewards": -2.018900803711465,
    "random_rewards": -1.3433080118715504,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.032784395223865,
    "equal_rewards": -2.0594150010298726,
    "random_rewards": -1.2046507874802628,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.006708693358003,
    "equal_rewards": -2.060154748294572,
    "random_rewards": -1.0474329681315089,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0048695569720665,
    "equal_rewards": -2.055909663440456,
    "random_rewards": -2.233199815208261,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0178442984181775,
    "equal_rewards": -2.0425296179697585,
    "random_rewards": -1.9673374127419918,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0058988168976644,
    "equal_rewards": -2.045689939618564,
    "random_rewards": -1.6315248029644946,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.025554261307501,
    "equal_rewards": -2.0456588468914862,
    "random_rewards": -1.9825535503328624,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0184932354123193,
    "equal_rewards": -2.076556002106342,
    "random_rewards": -2.7349761978961573,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0456594228286415,
    "equal_rewards": -2.0322859133299986,
    "random_rewards": -1.2109383172550727,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.022683706281932,
    "equal_rewards": -2.0403584631088227,
    "random_rewards": -1.3728733058193112,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0471709611059046,
    "equal_rewards": -2.021699413774925,
    "random_rewards": -1.7626913333167902,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0185912547939777,
    "equal_rewards": -2.069368867845656,
    "random_rewards": -2.7255102161869615,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0345306092142614,
    "equal_rewards": -2.059010075535965,
    "random_rewards": -1.9712082207407837,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0220489543406623,
    "equal_rewards": -2.055571126156693,
    "random_rewards": -2.394967558835231,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.024494017258748,
    "equal_rewards": -2.0538156827416585,
    "random_rewards": -1.0335810000510675,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.01613759578364,
    "equal_rewards": -2.0648090243057746,
    "random_rewards": -1.7815982148489082,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.006565221034653,
    "equal_rewards": -2.071946581473899,
    "random_rewards": -2.7231219347484643,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.072753312382447,
    "equal_rewards": -2.0354474050890645,
    "random_rewards": -1.9449757591949801,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0600872827747123,
    "equal_rewards": -2.040997682748136,
    "random_rewards": -1.768324526099954,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016849539159062,
    "equal_rewards": -2.070470636882402,
    "random_rewards": -1.839911557241259,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0279680440333556,
    "equal_rewards": -2.0439741397815405,
    "random_rewards": -1.823948121020409,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0197976726887292,
    "equal_rewards": -2.0484221766926796,
    "random_rewards": -2.0987338688808417,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0466722101937305,
    "equal_rewards": -2.0189097536753815,
    "random_rewards": -2.0603039257423346,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021869799823328,
    "equal_rewards": -2.0407651664564725,
    "random_rewards": -1.9233252724447278,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.041750538092196,
    "equal_rewards": -2.058466838839301,
    "random_rewards": -1.795119801254732,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.009054894584549,
    "equal_rewards": -2.0493009810397123,
    "random_rewards": -2.2492327840679764,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.018058502359462,
    "equal_rewards": -2.0382845997220866,
    "random_rewards": -1.7522090764806553,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0210457287850447,
    "equal_rewards": -2.0461265380993767,
    "random_rewards": -2.7030447399495423,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0060570753330644,
    "equal_rewards": -2.061606731093101,
    "random_rewards": -2.714448401459145,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011257363176979,
    "equal_rewards": -2.0795395142630126,
    "random_rewards": -1.704502789506079,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0764557473621568,
    "equal_rewards": -2.051264810701875,
    "random_rewards": -1.8080635109630834,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0219776431845657,
    "equal_rewards": -2.0777338511747407,
    "random_rewards": -1.378334295430374,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0699661045888207,
    "equal_rewards": -2.050658078062233,
    "random_rewards": -1.3779230061246102,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0140601149084287,
    "equal_rewards": -2.066881414478975,
    "random_rewards": -1.7986870357202638,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0285142248048667,
    "equal_rewards": -2.0453912965827707,
    "random_rewards": -1.9744429736859055,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.044176637254495,
    "equal_rewards": -2.0340173012901785,
    "random_rewards": -2.6708298244738806,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011443196785047,
    "equal_rewards": -2.0746864323739183,
    "random_rewards": -2.141500562776897,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.044373639385011,
    "equal_rewards": -2.069187997600726,
    "random_rewards": -1.94784012657883,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0240276739025314,
    "equal_rewards": -2.0527029384347557,
    "random_rewards": -1.78125162973478,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.057582892747997,
    "equal_rewards": -2.0144311465639513,
    "random_rewards": -1.618306937819471,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0718265971433296,
    "equal_rewards": -2.0438685389243925,
    "random_rewards": -1.938074582387035,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.034701014024614,
    "equal_rewards": -2.0640076156629577,
    "random_rewards": -1.9532127205185885,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0165307615505754,
    "equal_rewards": -2.072603007215573,
    "random_rewards": -1.6958788334650337,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0416577969876673,
    "equal_rewards": -2.068165175650619,
    "random_rewards": -1.491188924407715,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0263236485414717,
    "equal_rewards": -2.06782821076127,
    "random_rewards": -2.723227575845616,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0366339354104257,
    "equal_rewards": -2.0535078224519103,
    "random_rewards": -2.6932521515138346,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0450981372337393,
    "equal_rewards": -2.0660872634755956,
    "random_rewards": -0.9013702812196103,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0290773717199952,
    "equal_rewards": -2.075452551448473,
    "random_rewards": -1.527296096556254,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.068693808092386,
    "equal_rewards": -2.0491834300958898,
    "random_rewards": -1.1979864587515205,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021503840183094,
    "equal_rewards": -2.0699390434369573,
    "random_rewards": -1.983503170480828,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.032860515357281,
    "equal_rewards": -2.061490763787282,
    "random_rewards": -1.355392784661535,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0508465633247535,
    "equal_rewards": -2.0383145450863944,
    "random_rewards": -1.7862925424467502,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.05056529032999,
    "equal_rewards": -2.034767468016618,
    "random_rewards": -1.3570062901765358,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0162595433521258,
    "equal_rewards": -2.062168216923976,
    "random_rewards": -1.3514476116847483,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011108431322663,
    "equal_rewards": -2.0667953357535795,
    "random_rewards": -1.9863249240991432,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0580505725550724,
    "equal_rewards": -2.0420939537020564,
    "random_rewards": -1.3518303044758615,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0138942818405123,
    "equal_rewards": -2.0675264242178426,
    "random_rewards": -2.586402579701298,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.032305536400452,
    "equal_rewards": -2.059192615254049,
    "random_rewards": -2.1098618732114747,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.032645318701638,
    "equal_rewards": -2.0592840469670604,
    "random_rewards": -1.9460124497489244,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9959988037474337,
    "equal_rewards": -2.0591484110504368,
    "random_rewards": -1.3825836203701456,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.015574889846662,
    "equal_rewards": -2.045087059283166,
    "random_rewards": -1.6444572796762396,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0583070467478297,
    "equal_rewards": -2.0389587755499976,
    "random_rewards": -1.0453695442651625,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0463652263526546,
    "equal_rewards": -2.032972728183669,
    "random_rewards": -2.231311530933295,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0361149387287028,
    "equal_rewards": -2.0577213945689814,
    "random_rewards": -2.266852290905385,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0412409822945343,
    "equal_rewards": -2.049918608257957,
    "random_rewards": -1.51598816528071,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0153945059941125,
    "equal_rewards": -2.0661763128211215,
    "random_rewards": -1.7910591859684164,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0097752498557115,
    "equal_rewards": -2.070845372079473,
    "random_rewards": -1.3511280949490745,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.038967983614949,
    "equal_rewards": -2.0634448172158733,
    "random_rewards": -1.7900720092072777,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0663054067103186,
    "equal_rewards": -2.0414683902802793,
    "random_rewards": -1.9141747299944631,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.065372841985342,
    "equal_rewards": -2.0495873267011264,
    "random_rewards": -1.2157391798910162,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0458001858527473,
    "equal_rewards": -2.032970413972104,
    "random_rewards": -1.761077069110492,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.995436922914231,
    "equal_rewards": -2.0514606534947633,
    "random_rewards": -1.7729264371738078,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0428987109579935,
    "equal_rewards": -2.0272865830082085,
    "random_rewards": -1.9117327531017039,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0220496467746396,
    "equal_rewards": -2.0568421617001507,
    "random_rewards": -1.6784168780805337,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0071898828590906,
    "equal_rewards": -2.068148197273316,
    "random_rewards": -1.5326633165203591,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.040482848041246,
    "equal_rewards": -2.065286687963552,
    "random_rewards": -0.9001050015646356,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.057969842959203,
    "equal_rewards": -2.042057164063906,
    "random_rewards": -1.3515133753250042,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.009959579847716,
    "equal_rewards": -2.077466869205842,
    "random_rewards": -1.0737520038502137,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0599126289323584,
    "equal_rewards": -2.023165853980285,
    "random_rewards": -0.5875184609944353,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9979369516474292,
    "equal_rewards": -2.059018284924372,
    "random_rewards": -1.9485893512450105,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0432592128891254,
    "equal_rewards": -2.0357944955489886,
    "random_rewards": -2.2271106988334655,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0153845444308676,
    "equal_rewards": -2.0687603916854176,
    "random_rewards": -2.2473573891831125,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0105794975932114,
    "equal_rewards": -2.068929036877469,
    "random_rewards": -2.862118486579226,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0486676322412403,
    "equal_rewards": -2.0366410912538897,
    "random_rewards": -2.9869946385598127,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.042655435741511,
    "equal_rewards": -2.013942499816139,
    "random_rewards": -1.9184950481316145,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0392041754012484,
    "equal_rewards": -2.063944131095689,
    "random_rewards": -2.559672252347213,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.038898682335465,
    "equal_rewards": -2.062138842169921,
    "random_rewards": -2.1149969475049533,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0464933965783287,
    "equal_rewards": -2.033125009044254,
    "random_rewards": -1.6495947249302891,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0087253348179352,
    "equal_rewards": -2.0619139930561423,
    "random_rewards": -2.2563008115728254,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0075446952387,
    "equal_rewards": -2.067940822639456,
    "random_rewards": -1.8262886935428964,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0549791870962095,
    "equal_rewards": -2.042776205010263,
    "random_rewards": -1.9201143314946993,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.014265883058022,
    "equal_rewards": -2.0651802076574906,
    "random_rewards": -1.6479081481950413,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.029957226784161,
    "equal_rewards": -2.0469166071572613,
    "random_rewards": -2.1307094324634654,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0205651348478497,
    "equal_rewards": -2.040367285626248,
    "random_rewards": -2.2610708494275458,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.041066095375009,
    "equal_rewards": -2.021842499155853,
    "random_rewards": -0.8841415233215993,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.008689581779958,
    "equal_rewards": -2.0719895899916834,
    "random_rewards": -2.1156539068748224,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0222084967688922,
    "equal_rewards": -2.0698064145978243,
    "random_rewards": -1.045585146442758,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.027570404961131,
    "equal_rewards": -2.045186527124416,
    "random_rewards": -1.780227200009468,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0207870392797163,
    "equal_rewards": -2.0474892637015385,
    "random_rewards": -1.9839290477017348,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0591792937672952,
    "equal_rewards": -2.043237934205826,
    "random_rewards": -1.6434809264632917,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0164342755918585,
    "equal_rewards": -2.0702214362249176,
    "random_rewards": -1.485003704860603,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.030421873750484,
    "equal_rewards": -2.0429240339668184,
    "random_rewards": -1.0476478766298531,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9975997622681168,
    "equal_rewards": -2.05816158922906,
    "random_rewards": -1.9607848524708646,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0428266319038975,
    "equal_rewards": -2.0678772005102806,
    "random_rewards": -2.1105926839449207,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011729621210341,
    "equal_rewards": -2.0460611238814956,
    "random_rewards": -2.08824426409633,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0253404273428113,
    "equal_rewards": -2.007228712512289,
    "random_rewards": -2.0720281250406565,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9966291583227644,
    "equal_rewards": -2.0524449379786214,
    "random_rewards": -2.4183319325405837,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.036540513408951,
    "equal_rewards": -2.063240702554972,
    "random_rewards": -0.9058129913655973,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0134054127110015,
    "equal_rewards": -2.0484198025505176,
    "random_rewards": -1.6631503686195115,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9905958986320487,
    "equal_rewards": -2.0585243591696623,
    "random_rewards": -1.779016103622699,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.059076377370363,
    "equal_rewards": -2.0537819546457636,
    "random_rewards": -0.8835811779961646,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.043655633463774,
    "equal_rewards": -2.0206258635715866,
    "random_rewards": -1.1615714620210427,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0531097064929846,
    "equal_rewards": -2.0340161926189095,
    "random_rewards": -0.9030391480546419,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0184108378825356,
    "equal_rewards": -2.0692185332526267,
    "random_rewards": -2.0891703050775927,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0092032974567586,
    "equal_rewards": -2.0469465627902412,
    "random_rewards": -2.5469440209679317,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.997017799143134,
    "equal_rewards": -2.050533050008767,
    "random_rewards": -2.243751365494911,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0475278561425796,
    "equal_rewards": -2.02693483796774,
    "random_rewards": -2.2079609109150122,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9999203433830017,
    "equal_rewards": -2.0375033288253026,
    "random_rewards": -1.5230264348098363,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.036040453091046,
    "equal_rewards": -2.062532566157601,
    "random_rewards": -2.2731343040194885,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010388073129028,
    "equal_rewards": -2.06654340560417,
    "random_rewards": -1.0423819089252357,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011754602116415,
    "equal_rewards": -2.0651154526478974,
    "random_rewards": -1.9798404759164752,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0646627516680014,
    "equal_rewards": -2.0260997403692187,
    "random_rewards": -2.226865927647657,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.045406970747245,
    "equal_rewards": -2.0644549609918137,
    "random_rewards": -1.6711614642656383,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0194195227117544,
    "equal_rewards": -2.057171912742475,
    "random_rewards": -1.3331052695572523,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.017230557827684,
    "equal_rewards": -2.038741903191961,
    "random_rewards": -1.8256700700332624,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0428385640522984,
    "equal_rewards": -2.0375354311737777,
    "random_rewards": -1.1949627980510231,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9886819398291409,
    "equal_rewards": -2.056744217597128,
    "random_rewards": -1.9147989870773094,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0404804224881334,
    "equal_rewards": -2.0249468471172505,
    "random_rewards": -2.3771736097732985,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.026379019148555,
    "equal_rewards": -2.0549124885243737,
    "random_rewards": -0.7510635780419816,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.052701850589646,
    "equal_rewards": -2.0336411144274233,
    "random_rewards": -1.4860637270761474,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0181836367187627,
    "equal_rewards": -2.0664132628776493,
    "random_rewards": -2.4425806134197146,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0567693204895474,
    "equal_rewards": -2.037598196394799,
    "random_rewards": -1.3316857781994567,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.028761172201838,
    "equal_rewards": -2.0453335116718763,
    "random_rewards": -2.108774825550292,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.00755381103067,
    "equal_rewards": -2.060945068556495,
    "random_rewards": -2.0943287869225777,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0343652538246477,
    "equal_rewards": -2.057310433535428,
    "random_rewards": -1.9398112456000585,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0252562070574935,
    "equal_rewards": -2.0543936414225867,
    "random_rewards": -1.6752991452160912,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0085191381681913,
    "equal_rewards": -2.0691183419793115,
    "random_rewards": -1.3772696249249585,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0137851564643725,
    "equal_rewards": -2.0695186028775745,
    "random_rewards": -2.2763644875216924,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0385248715045687,
    "equal_rewards": -2.0615393375926763,
    "random_rewards": -2.0958836394600393,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0136674495814852,
    "equal_rewards": -2.067301593876541,
    "random_rewards": -2.259453992466634,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0604513187274422,
    "equal_rewards": -2.0447403482857203,
    "random_rewards": -1.6309835783645856,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0256072798178577,
    "equal_rewards": -2.036316882472021,
    "random_rewards": -1.8126522228365731,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.040025578857741,
    "equal_rewards": -2.017578013232033,
    "random_rewards": -1.9212276275494102,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0121416597001356,
    "equal_rewards": -2.072929185998984,
    "random_rewards": -1.526921415344584,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0583752888899247,
    "equal_rewards": -2.0302387694515094,
    "random_rewards": -1.165252496867506,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021159777055581,
    "equal_rewards": -2.0398065495246964,
    "random_rewards": -1.6372790626481044,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011936157514289,
    "equal_rewards": -2.0699456259541704,
    "random_rewards": -1.9740205823449277,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0614930478471543,
    "equal_rewards": -2.042469281255417,
    "random_rewards": -1.4621624292174835,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0165048869036513,
    "equal_rewards": -2.0674408178452173,
    "random_rewards": -1.695081539658975,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0076373657036735,
    "equal_rewards": -2.0683732159536534,
    "random_rewards": -1.9619357407444589,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010072379244324,
    "equal_rewards": -2.0754969497835187,
    "random_rewards": -2.0964313433246207,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.065265977756651,
    "equal_rewards": -2.028812514543972,
    "random_rewards": -2.3563488177728193,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0371494582762395,
    "equal_rewards": -2.0218168460159798,
    "random_rewards": -1.621633434000221,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004140274483304,
    "equal_rewards": -2.0673647352126507,
    "random_rewards": -1.6571021315906855,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0628486662945225,
    "equal_rewards": -2.0263475760222427,
    "random_rewards": -0.8930785398623993,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0396496987341326,
    "equal_rewards": -2.0611249809509573,
    "random_rewards": -2.2705748608568843,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.04465997165518,
    "equal_rewards": -2.026547865251561,
    "random_rewards": -1.3420903258642833,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.990015721520539,
    "equal_rewards": -2.0484380329261285,
    "random_rewards": -1.3638252548567324,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.035976272003453,
    "equal_rewards": -2.0606713551986933,
    "random_rewards": -2.1114551010695863,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013177948780415,
    "equal_rewards": -2.0690065191560953,
    "random_rewards": -1.3409482050280985,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.042928405895488,
    "equal_rewards": -2.032888018099616,
    "random_rewards": -1.924080276007769,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.005635705573258,
    "equal_rewards": -2.0690503288754325,
    "random_rewards": -1.1810691952936876,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0115243591708363,
    "equal_rewards": -2.064988616654667,
    "random_rewards": -1.6795179096901582,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0118725727156783,
    "equal_rewards": -2.032073501798232,
    "random_rewards": -1.7506223260991538,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0117491818059636,
    "equal_rewards": -2.038322330173651,
    "random_rewards": -1.3652656891173374,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.034194380563304,
    "equal_rewards": -2.0429705235850992,
    "random_rewards": -1.9482168692134487,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0446277133673116,
    "equal_rewards": -2.0258816584106873,
    "random_rewards": -2.6644319044022877,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0212688923520385,
    "equal_rewards": -2.0465149912004046,
    "random_rewards": -1.6702440533681269,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.008333441602164,
    "equal_rewards": -2.0667780072703468,
    "random_rewards": -2.129408636871166,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.062909586041509,
    "equal_rewards": -2.040549800284874,
    "random_rewards": -1.7747455749227483,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0157194239676084,
    "equal_rewards": -2.06912362314967,
    "random_rewards": -1.3475736744688522,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0142411812260095,
    "equal_rewards": -2.06285271464676,
    "random_rewards": -2.4082740535655125,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0175729395020583,
    "equal_rewards": -2.050347095955127,
    "random_rewards": -1.619638562621177,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.038329777690244,
    "equal_rewards": -2.0218680934922206,
    "random_rewards": -2.397740215056269,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9979515885228458,
    "equal_rewards": -2.04896940816931,
    "random_rewards": -2.05441090490735,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.05292934480834,
    "equal_rewards": -2.036911225187866,
    "random_rewards": -1.3070739249119243,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9986577069136497,
    "equal_rewards": -2.061683364588369,
    "random_rewards": -2.0700554058788576,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0620775202333532,
    "equal_rewards": -2.036712632031688,
    "random_rewards": -1.9090676831824926,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0169396788120513,
    "equal_rewards": -2.078019567623807,
    "random_rewards": -1.3366778844476717,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0491573616982186,
    "equal_rewards": -2.031657267317286,
    "random_rewards": -1.6107061290350169,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0125102588228483,
    "equal_rewards": -2.039484088553691,
    "random_rewards": -2.0993414442235103,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.043572292984991,
    "equal_rewards": -2.042063994199453,
    "random_rewards": -2.6786768929510574,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.017822998531722,
    "equal_rewards": -2.0737937727565012,
    "random_rewards": -2.898602977546354,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0480478868018492,
    "equal_rewards": -2.073434108350145,
    "random_rewards": -1.507357054649988,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0445791074831723,
    "equal_rewards": -2.0691352396110974,
    "random_rewards": -1.8240309079879493,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.025445124326367,
    "equal_rewards": -2.0503826121620397,
    "random_rewards": -1.8286706060045848,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.018282894679851,
    "equal_rewards": -2.034083644133223,
    "random_rewards": -2.2325308289267083,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0035042633126934,
    "equal_rewards": -2.0368977605900938,
    "random_rewards": -1.6509229709152373,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.027096419868256,
    "equal_rewards": -2.0479307251687,
    "random_rewards": -1.7981830757578827,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0373852151401817,
    "equal_rewards": -2.058515244086976,
    "random_rewards": -1.6302770305922283,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.002471295740827,
    "equal_rewards": -2.058129696704642,
    "random_rewards": -2.1475277739440877,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.031885543054741,
    "equal_rewards": -2.0157450218330486,
    "random_rewards": -2.1968535747494284,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0053843924219477,
    "equal_rewards": -2.064205174817471,
    "random_rewards": -1.8253829550432732,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0085139494023583,
    "equal_rewards": -2.069027773361406,
    "random_rewards": -1.9395497298858233,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.072595840767389,
    "equal_rewards": -2.034386571122463,
    "random_rewards": -1.9165919190037357,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.008546101341174,
    "equal_rewards": -2.064357388153633,
    "random_rewards": -2.163177166587857,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0061855741655927,
    "equal_rewards": -2.059855845876894,
    "random_rewards": -1.9349446893384274,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0342209160911247,
    "equal_rewards": -2.023122051867085,
    "random_rewards": -2.3430703192923437,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.996756518700487,
    "equal_rewards": -2.0420239441503076,
    "random_rewards": -1.6139384758183866,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9918370742730276,
    "equal_rewards": -2.0479923501706097,
    "random_rewards": -1.9269716138320754,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0567981763824608,
    "equal_rewards": -2.0218225580376536,
    "random_rewards": -2.0931833804774103,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.03645449843049,
    "equal_rewards": -2.0553241202503916,
    "random_rewards": -2.0777140039575994,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.038475385868176,
    "equal_rewards": -2.0474872959431014,
    "random_rewards": -2.8368080193638385,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000355532278652,
    "equal_rewards": -2.0406300730037326,
    "random_rewards": -2.524544689755265,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0414025050348985,
    "equal_rewards": -2.0033673623305885,
    "random_rewards": -0.8688297507961344,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0322399813925798,
    "equal_rewards": -2.0536877265545086,
    "random_rewards": -0.752070206035194,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0266167421347703,
    "equal_rewards": -2.0516782690650093,
    "random_rewards": -1.9577444852252912,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.005683330773114,
    "equal_rewards": -2.0594115014434413,
    "random_rewards": -2.4168598443827705,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9995768407414354,
    "equal_rewards": -2.044501283246059,
    "random_rewards": -1.1899253047087055,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9982166492281246,
    "equal_rewards": -2.0490041455434924,
    "random_rewards": -1.2071467694760316,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0029664023974982,
    "equal_rewards": -2.0686564679211132,
    "random_rewards": -2.135480718352219,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011209662668691,
    "equal_rewards": -2.046396607737799,
    "random_rewards": -2.073431937575488,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9930386519153993,
    "equal_rewards": -2.0410262136358326,
    "random_rewards": -2.074586138041481,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0055797397193693,
    "equal_rewards": -2.059282544549093,
    "random_rewards": -2.8633844450265062,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.022722192704535,
    "equal_rewards": -2.03513350719742,
    "random_rewards": -1.049855960951488,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9921634203862788,
    "equal_rewards": -2.0479242521522574,
    "random_rewards": -1.925398562432654,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0519606083718758,
    "equal_rewards": -2.0329844535911343,
    "random_rewards": -1.622185419615139,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0098124061093254,
    "equal_rewards": -2.065320331982278,
    "random_rewards": -2.2306156511012727,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.049652268966375,
    "equal_rewards": -2.027714053605608,
    "random_rewards": -0.5932856704111473,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.003561989531357,
    "equal_rewards": -2.009888155964871,
    "random_rewards": -1.1946214136499902,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9827006670961063,
    "equal_rewards": -2.0282375913974944,
    "random_rewards": -2.812125310501172,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0439367520235487,
    "equal_rewards": -2.0215033391410415,
    "random_rewards": -1.7944551618425166,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013158488889202,
    "equal_rewards": -2.0665073864375136,
    "random_rewards": -1.3554925565001137,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010982599583434,
    "equal_rewards": -2.0644977608745316,
    "random_rewards": -1.3541539233188558,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0103213149787362,
    "equal_rewards": -2.0430466299154633,
    "random_rewards": -1.8003812200235654,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9959127542046744,
    "equal_rewards": -2.0444262599225347,
    "random_rewards": -2.3917815772537114,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0267682211506997,
    "equal_rewards": -2.055406932235109,
    "random_rewards": -2.2629251402194575,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.022551342790709,
    "equal_rewards": -2.0403069958502518,
    "random_rewards": -2.0815708431344784,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9966460126659236,
    "equal_rewards": -2.050236059213827,
    "random_rewards": -1.8084833374903666,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0514095145678275,
    "equal_rewards": -2.0269830260363233,
    "random_rewards": -0.7526255895290196,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.997437835059278,
    "equal_rewards": -2.048434111656185,
    "random_rewards": -1.5073516712901327,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0164044778485612,
    "equal_rewards": -2.0501009728302924,
    "random_rewards": -0.756768513543625,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.005081370676779,
    "equal_rewards": -2.073327337968489,
    "random_rewards": -2.154589904874195,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.05637070249848,
    "equal_rewards": -2.0358455729622835,
    "random_rewards": -1.4996128878696202,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011564821445349,
    "equal_rewards": -2.0626558218440074,
    "random_rewards": -2.134602044487589,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021243217291041,
    "equal_rewards": -2.049843495774423,
    "random_rewards": -2.5792743821194004,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0477600401341545,
    "equal_rewards": -2.01977319025073,
    "random_rewards": -2.0484012152862907,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.018861130886871,
    "equal_rewards": -2.048091997218992,
    "random_rewards": -1.4685813974731778,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0320568797648395,
    "equal_rewards": -2.058680070748297,
    "random_rewards": -1.8170549519214299,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0222078979477365,
    "equal_rewards": -2.0517503712252005,
    "random_rewards": -2.8540614160221174,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0361655076753773,
    "equal_rewards": -2.064804776644814,
    "random_rewards": -2.2430533049390213,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.995779791554092,
    "equal_rewards": -2.051232777135771,
    "random_rewards": -1.9367403357646669,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.025189732940282,
    "equal_rewards": -2.007031734834117,
    "random_rewards": -2.6612160372380598,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0124285534275654,
    "equal_rewards": -2.040979269417843,
    "random_rewards": -1.0519433823521687,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0106127892501986,
    "equal_rewards": -2.0669428400757224,
    "random_rewards": -1.3611574800498658,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0142794194698626,
    "equal_rewards": -2.0568140035802873,
    "random_rewards": -2.401096790977729,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.049738930272371,
    "equal_rewards": -2.0291082012791195,
    "random_rewards": -1.3248276554760756,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007234525806453,
    "equal_rewards": -2.0610102359282636,
    "random_rewards": -2.578338692048301,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0148837327255333,
    "equal_rewards": -2.0307340367354993,
    "random_rewards": -2.082155370972237,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.005969010336177,
    "equal_rewards": -2.0387242891456454,
    "random_rewards": -2.6929975481877233,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004583516539552,
    "equal_rewards": -2.0632576109498846,
    "random_rewards": -1.6768898942806025,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010529635060287,
    "equal_rewards": -2.0567377845987265,
    "random_rewards": -1.6812297171343817,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0368970922167016,
    "equal_rewards": -2.061739558445656,
    "random_rewards": -2.2661239681486363,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.039615712887302,
    "equal_rewards": -2.021457932693603,
    "random_rewards": -1.4528943772102365,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9775965324983684,
    "equal_rewards": -2.038628439337648,
    "random_rewards": -2.2353023072240057,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0550614102618243,
    "equal_rewards": -2.02971150385139,
    "random_rewards": -2.084507557152393,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0242680909834463,
    "equal_rewards": -2.050879700667772,
    "random_rewards": -1.4907952395789499,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9875130398463992,
    "equal_rewards": -2.045967281310936,
    "random_rewards": -2.686298418868208,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.04410477570151,
    "equal_rewards": -2.031836797445689,
    "random_rewards": -2.0697569878732054,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0381153414042563,
    "equal_rewards": -2.033867250891813,
    "random_rewards": -1.7929011158270862,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.046301191158894,
    "equal_rewards": -2.0652158554581947,
    "random_rewards": -1.6461874031256838,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0379106403099865,
    "equal_rewards": -2.0545273202230567,
    "random_rewards": -1.489863019426993,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.030351947608119,
    "equal_rewards": -2.057016394499346,
    "random_rewards": -1.9548118138419566,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.012771420311899,
    "equal_rewards": -2.0659749208650275,
    "random_rewards": -2.1063556907871597,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0052863376184016,
    "equal_rewards": -2.035460577510487,
    "random_rewards": -2.1149456311053765,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0068993551815706,
    "equal_rewards": -2.0356230590102196,
    "random_rewards": -1.6769795418868427,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0464483095003376,
    "equal_rewards": -2.0374617443283003,
    "random_rewards": -1.3417430999235147,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007303212065887,
    "equal_rewards": -2.0624498455754954,
    "random_rewards": -0.8907224265881115,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.066001677141996,
    "equal_rewards": -2.03809660352564,
    "random_rewards": -2.5378464979175384,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0136881775671958,
    "equal_rewards": -2.0601664309208125,
    "random_rewards": -2.437723061932752,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.009747475982313,
    "equal_rewards": -2.063397730438155,
    "random_rewards": -1.345182302373456,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.009675110409914,
    "equal_rewards": -2.0607357267918918,
    "random_rewards": -2.293270561874967,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.001964454086272,
    "equal_rewards": -2.0652444611391774,
    "random_rewards": -2.0820392995692725,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.012661364511162,
    "equal_rewards": -2.045250082163819,
    "random_rewards": -2.3722296822476654,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9859451625721007,
    "equal_rewards": -2.044071960214228,
    "random_rewards": -1.3627823448021033,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0543071719482775,
    "equal_rewards": -2.0215472049578933,
    "random_rewards": -2.3478888916979486,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.033885015156591,
    "equal_rewards": -2.058571318872835,
    "random_rewards": -1.4843035092982708,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0455561978860586,
    "equal_rewards": -2.0288673696088066,
    "random_rewards": -2.070855398634162,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0325838924113495,
    "equal_rewards": -2.0165291098214535,
    "random_rewards": -1.909176708628685,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0226606100936446,
    "equal_rewards": -2.0533883119589538,
    "random_rewards": -0.7506240682971785,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0013302133354736,
    "equal_rewards": -2.062243656912331,
    "random_rewards": -1.2001674698414921,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0114582110485326,
    "equal_rewards": -2.067267190031578,
    "random_rewards": -1.057693083185586,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0379576635695296,
    "equal_rewards": -2.059591025392763,
    "random_rewards": -1.5377309259286274,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0113131291776076,
    "equal_rewards": -2.0696395730740047,
    "random_rewards": -2.3012153153839847,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0611004670603426,
    "equal_rewards": -2.021996484322595,
    "random_rewards": -1.9157230644422167,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.057866621738031,
    "equal_rewards": -2.019822385138961,
    "random_rewards": -0.8721213004240399,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0234528242613514,
    "equal_rewards": -2.0521199760152764,
    "random_rewards": -2.2512819968103246,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.002751301108703,
    "equal_rewards": -2.065868924717883,
    "random_rewards": -2.127560537512744,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.009448880649384,
    "equal_rewards": -2.072979983554949,
    "random_rewards": -0.7722104950453821,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0573381610220007,
    "equal_rewards": -2.0415874903565374,
    "random_rewards": -1.6455719912326554,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.008892022247628,
    "equal_rewards": -2.0623502261895963,
    "random_rewards": -2.253811856255834,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0078954127130744,
    "equal_rewards": -2.054921919754642,
    "random_rewards": -1.3541497914672538,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0261409604071248,
    "equal_rewards": -2.0101088433371688,
    "random_rewards": -0.7285426932662382,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.029287717423767,
    "equal_rewards": -2.005532264636172,
    "random_rewards": -2.1950988920589034,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9965399785029756,
    "equal_rewards": -2.0548323956666468,
    "random_rewards": -1.6532325096119873,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0396275334568363,
    "equal_rewards": -2.0627634997229705,
    "random_rewards": -2.264008719208138,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9675995458597875,
    "equal_rewards": -2.0439288297915703,
    "random_rewards": -2.1232059977946838,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.017301036229077,
    "equal_rewards": -1.9892059138039209,
    "random_rewards": -1.587342655264352,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0220498240022087,
    "equal_rewards": -2.0754555880054286,
    "random_rewards": -2.7403505372723425,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0166590032163834,
    "equal_rewards": -2.0673910132653304,
    "random_rewards": -0.5973848367191993,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0182301648619765,
    "equal_rewards": -2.064227923844033,
    "random_rewards": -0.6044088612021471,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011012902511019,
    "equal_rewards": -2.02852610704958,
    "random_rewards": -2.6934430820886215,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0147107388388843,
    "equal_rewards": -2.001762820396447,
    "random_rewards": -1.9260229330337202,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9497987712076914,
    "equal_rewards": -2.0220463929560863,
    "random_rewards": -0.8898028901795056,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9878327714930561,
    "equal_rewards": -1.9725430316437922,
    "random_rewards": -1.585117853162588,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9851336343536263,
    "equal_rewards": -2.043350346757749,
    "random_rewards": -1.1992410145258894,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0272786768424833,
    "equal_rewards": -2.0538898633702374,
    "random_rewards": -2.1328271004797323,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.049989417550118,
    "equal_rewards": -2.0377184233170658,
    "random_rewards": -1.3630209274582197,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.002178064415915,
    "equal_rewards": -2.0662008195138917,
    "random_rewards": -1.6740416507157225,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.034432155062126,
    "equal_rewards": -1.994278472475321,
    "random_rewards": -1.5948386551255198,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.937928956051231,
    "equal_rewards": -1.959149300853111,
    "random_rewards": -1.313719392078132,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9669051195741445,
    "equal_rewards": -1.9979521992281977,
    "random_rewards": -1.3351158120028188,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9997223810759504,
    "equal_rewards": -2.0649887567211698,
    "random_rewards": -1.6696955458192932,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.060310127249076,
    "equal_rewards": -2.030033615101669,
    "random_rewards": -1.051095606231924,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9972845429268022,
    "equal_rewards": -2.050483259456858,
    "random_rewards": -2.4241999674385246,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0407851225978373,
    "equal_rewards": -2.022686303054713,
    "random_rewards": -2.2302781863182815,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0167710526623623,
    "equal_rewards": -2.0432827410739085,
    "random_rewards": -1.9364231245749206,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0134565635873396,
    "equal_rewards": -2.066892587502805,
    "random_rewards": -1.989714532593283,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.052696349134965,
    "equal_rewards": -2.0368913160383397,
    "random_rewards": -1.778176012455075,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.012381764290489,
    "equal_rewards": -2.0676893097754947,
    "random_rewards": -1.9739605156083335,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0438627019553137,
    "equal_rewards": -2.06308783182202,
    "random_rewards": -1.7041733713057161,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.025398740001336,
    "equal_rewards": -2.07590781986287,
    "random_rewards": -1.9981259281637094,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0215513127848617,
    "equal_rewards": -2.0481969640483397,
    "random_rewards": -0.7646678047353423,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9796539668098498,
    "equal_rewards": -2.043800712054207,
    "random_rewards": -2.5501076129586524,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.001783647885875,
    "equal_rewards": -2.0386913211231366,
    "random_rewards": -1.3658157927927848,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.018400019417884,
    "equal_rewards": -2.070691029690802,
    "random_rewards": -1.6790484847607559,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0424015509643194,
    "equal_rewards": -2.0207269854586185,
    "random_rewards": -2.9510380177842115,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0165274726003686,
    "equal_rewards": -1.998347451638033,
    "random_rewards": -2.5042052431420494,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.015141642052516,
    "equal_rewards": -2.0398134601965774,
    "random_rewards": -2.9856138767179234,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0128629047019233,
    "equal_rewards": -2.0776774707953756,
    "random_rewards": -0.9064443900862308,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0496850400761204,
    "equal_rewards": -2.037897277954313,
    "random_rewards": -0.7520248150213508,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9979748382884306,
    "equal_rewards": -2.0158537978715265,
    "random_rewards": -1.4391793559236206,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9908254817584918,
    "equal_rewards": -2.0448461666486804,
    "random_rewards": -1.1661087407196749,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.009936906548793,
    "equal_rewards": -2.063618739146901,
    "random_rewards": -2.446611632266271,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0486777353209593,
    "equal_rewards": -2.03608707222201,
    "random_rewards": -1.1976978316661995,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.04795670283885,
    "equal_rewards": -2.03503385419311,
    "random_rewards": -2.8197176089711222,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.051850437269988,
    "equal_rewards": -2.0361260983605054,
    "random_rewards": -1.7638176969552406,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.009262941896126,
    "equal_rewards": -2.0675860182547496,
    "random_rewards": -2.1385950882324405,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0114473890730413,
    "equal_rewards": -2.0434452496594724,
    "random_rewards": -0.7634368274533829,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.003053913777431,
    "equal_rewards": -2.055011748414147,
    "random_rewards": -1.5310455588905558,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0014406897637014,
    "equal_rewards": -2.0549684554486354,
    "random_rewards": -1.766006400383353,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0486903784688835,
    "equal_rewards": -2.0122605457893212,
    "random_rewards": -2.3717196903188325,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0567793839235624,
    "equal_rewards": -2.034448253702716,
    "random_rewards": -2.38625079538516,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.014754049096955,
    "equal_rewards": -2.0678185100186193,
    "random_rewards": -1.8140925918793043,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0088713863716796,
    "equal_rewards": -2.0629122131644686,
    "random_rewards": -1.2085762806442166,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0277528145880606,
    "equal_rewards": -2.056194953577957,
    "random_rewards": -2.060524737167472,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010987804031486,
    "equal_rewards": -2.0621358072331932,
    "random_rewards": -1.8270293856964623,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0463717687515426,
    "equal_rewards": -2.0196485940795506,
    "random_rewards": -0.8919052864538376,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9912665168186594,
    "equal_rewards": -2.052042258442159,
    "random_rewards": -2.845111993985121,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.015130660962724,
    "equal_rewards": -2.0333287513658282,
    "random_rewards": -1.8151116221501857,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000153308023776,
    "equal_rewards": -2.0266755335578654,
    "random_rewards": -2.0777806818405673,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0008570351428636,
    "equal_rewards": -2.0591971025676132,
    "random_rewards": -2.735346812143939,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.006729500322034,
    "equal_rewards": -2.044662699607362,
    "random_rewards": -1.8071586696612245,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.037286247539003,
    "equal_rewards": -2.022044201030092,
    "random_rewards": -1.1885984004229537,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0107994281571053,
    "equal_rewards": -2.066823249859831,
    "random_rewards": -2.290066178528364,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0362798953251295,
    "equal_rewards": -2.0561583169010778,
    "random_rewards": -2.5440712999502537,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0188564758961816,
    "equal_rewards": -2.066673488092502,
    "random_rewards": -1.0727197312252972,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0062469136802124,
    "equal_rewards": -2.059502075888758,
    "random_rewards": -1.937778023629861,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0013534915447506,
    "equal_rewards": -2.0492372731156876,
    "random_rewards": -2.22878058679125,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0513594819495546,
    "equal_rewards": -2.0105799514348677,
    "random_rewards": -2.0887476249406056,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.98972045280391,
    "equal_rewards": -2.045966915615046,
    "random_rewards": -2.201909235994748,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016242701412586,
    "equal_rewards": -2.0426510043413852,
    "random_rewards": -1.9506072520636906,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0208203664375777,
    "equal_rewards": -2.0426959327075194,
    "random_rewards": -1.7716044581242016,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0086302076866227,
    "equal_rewards": -2.033478224014261,
    "random_rewards": -1.6060269726617733,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.054966783840036,
    "equal_rewards": -2.0179863887552028,
    "random_rewards": -2.089460826633498,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0573925310159833,
    "equal_rewards": -2.0381045344511017,
    "random_rewards": -2.2434991355990865,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.025392512845545,
    "equal_rewards": -2.0546938946311655,
    "random_rewards": -2.2585829873312004,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.008072520634273,
    "equal_rewards": -2.071635706889915,
    "random_rewards": -1.070347798256778,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0500776696399043,
    "equal_rewards": -2.028069340843297,
    "random_rewards": -1.8967716289880847,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9926793723387837,
    "equal_rewards": -2.02638801632169,
    "random_rewards": -1.803103683231153,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011316048156596,
    "equal_rewards": -2.0643919522120013,
    "random_rewards": -1.05637914971978,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013632167728679,
    "equal_rewards": -2.06205803727378,
    "random_rewards": -2.7150134338858534,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.030406281468361,
    "equal_rewards": -2.056947450040396,
    "random_rewards": -1.9183337189893486,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0024045165971103,
    "equal_rewards": -2.068056282970025,
    "random_rewards": -2.703544358956457,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.038696658192906,
    "equal_rewards": -2.0643498085344882,
    "random_rewards": -1.8047477020774265,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.031660757697688,
    "equal_rewards": -2.0565554107082997,
    "random_rewards": -1.194218705245306,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0456262086455808,
    "equal_rewards": -2.02747633333288,
    "random_rewards": -1.178660385740558,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0406383873087885,
    "equal_rewards": -2.060969825821295,
    "random_rewards": -2.256271194375328,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021203352398209,
    "equal_rewards": -2.0792779432440893,
    "random_rewards": -1.3628372970977392,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9962269095477638,
    "equal_rewards": -2.0211959267090105,
    "random_rewards": -1.743266170698114,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9968793479293405,
    "equal_rewards": -2.0490367009717034,
    "random_rewards": -0.8957428816816465,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011856286042143,
    "equal_rewards": -2.079036494250392,
    "random_rewards": -2.1599599874034645,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.034680745454251,
    "equal_rewards": -2.067752021098969,
    "random_rewards": -2.2384229441748147,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0489463539158823,
    "equal_rewards": -2.0331463274511528,
    "random_rewards": -1.7956306215007687,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016737935461214,
    "equal_rewards": -2.0675964664752335,
    "random_rewards": -1.3603940785929232,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0687332915692838,
    "equal_rewards": -2.040388885354939,
    "random_rewards": -1.31265681575544,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.069133405640415,
    "equal_rewards": -2.049928616004184,
    "random_rewards": -1.4878130345681633,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0247640167154515,
    "equal_rewards": -2.0726726311624377,
    "random_rewards": -1.0909037416702831,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0304762359625306,
    "equal_rewards": -2.047079915573872,
    "random_rewards": -1.030021459488748,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0443295526330902,
    "equal_rewards": -2.0355383316250464,
    "random_rewards": -0.7328795506233443,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9994529427072336,
    "equal_rewards": -2.054002392942837,
    "random_rewards": -1.7642335102073758,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.020483646172179,
    "equal_rewards": -2.0453157973303524,
    "random_rewards": -1.9745850321390885,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.053528501853073,
    "equal_rewards": -2.0370000480569237,
    "random_rewards": -1.4677012667479206,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0203756084075506,
    "equal_rewards": -2.0488946477673786,
    "random_rewards": -1.3500042438109714,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0135769373762393,
    "equal_rewards": -2.067158776109269,
    "random_rewards": -2.0817407864398048,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.019132632498804,
    "equal_rewards": -2.0724863115950667,
    "random_rewards": -2.2309590717590106,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0144969954457492,
    "equal_rewards": -2.060253077294149,
    "random_rewards": -1.9607219263037263,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.017437206080073,
    "equal_rewards": -2.0426556308994455,
    "random_rewards": -1.6705052280557857,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.009445024040503,
    "equal_rewards": -2.073398102463554,
    "random_rewards": -2.002594285345664,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0158577873977186,
    "equal_rewards": -2.076675981655517,
    "random_rewards": -1.505524799411354,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0103548992022238,
    "equal_rewards": -2.078097601001432,
    "random_rewards": -1.6920041546302282,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0584490069317325,
    "equal_rewards": -2.0384341594343005,
    "random_rewards": -2.2303286706660366,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0440514129030194,
    "equal_rewards": -2.0631016179941484,
    "random_rewards": -2.385952882906129,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.019168785994893,
    "equal_rewards": -2.072346786818726,
    "random_rewards": -1.66074837398714,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0105217496463323,
    "equal_rewards": -2.0632543644135026,
    "random_rewards": -1.946868598459731,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.020947718621451,
    "equal_rewards": -2.036881284014735,
    "random_rewards": -2.0790370326846075,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0050370294590225,
    "equal_rewards": -2.0117900119438006,
    "random_rewards": -2.035659864990213,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.024644878330151,
    "equal_rewards": -2.0120679087731936,
    "random_rewards": -1.3389772785027416,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0095690127372365,
    "equal_rewards": -2.0625460772924167,
    "random_rewards": -1.8490271347065326,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0306095711377012,
    "equal_rewards": -2.059234726190131,
    "random_rewards": -1.3480305801935417,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.019680224597699,
    "equal_rewards": -2.0414959562352744,
    "random_rewards": -1.9498543812472748,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0022098401193302,
    "equal_rewards": -2.0553854254879127,
    "random_rewards": -2.4053350135685783,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0100578806861784,
    "equal_rewards": -2.075501080374995,
    "random_rewards": -1.6460884260823851,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.020746721609829,
    "equal_rewards": -2.0626674609812876,
    "random_rewards": -1.992496519123447,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0474495712949485,
    "equal_rewards": -2.0674324407655256,
    "random_rewards": -1.5286755379494257,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0678499572899813,
    "equal_rewards": -2.042374181227908,
    "random_rewards": -1.2043866754538595,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0383235147585386,
    "equal_rewards": -2.06454854056914,
    "random_rewards": -2.869740147890155,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.053778972006665,
    "equal_rewards": -2.0485308142363197,
    "random_rewards": -2.7159419259470665,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016057604500146,
    "equal_rewards": -2.0715937615239053,
    "random_rewards": -1.8271534402235179,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0181822485977134,
    "equal_rewards": -2.0713744854787604,
    "random_rewards": -1.9938677507764542,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0661631386089727,
    "equal_rewards": -2.0439537209064347,
    "random_rewards": -2.5380247430792227,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0742834173284423,
    "equal_rewards": -2.0458687547327568,
    "random_rewards": -1.6589124614974233,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.032875315670601,
    "equal_rewards": -2.061973515119015,
    "random_rewards": -1.7976054232077914,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0393048800419966,
    "equal_rewards": -2.0638710882166444,
    "random_rewards": -1.987037485218637,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0330392804137922,
    "equal_rewards": -2.066049029364439,
    "random_rewards": -1.8213111547831207,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0132357906516107,
    "equal_rewards": -2.066382325517369,
    "random_rewards": -1.496180197464665,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0351793967483154,
    "equal_rewards": -2.0618115728606234,
    "random_rewards": -1.9473391724290834,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0144174566222786,
    "equal_rewards": -2.0722928093165702,
    "random_rewards": -0.9015046941098748,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.035139525405807,
    "equal_rewards": -2.059850087677975,
    "random_rewards": -2.2482045060201528,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.01864327447023,
    "equal_rewards": -2.060550705128154,
    "random_rewards": -1.7971815028090212,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0432335884285857,
    "equal_rewards": -2.0646489116227698,
    "random_rewards": -2.2929516440923905,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.018590269007195,
    "equal_rewards": -2.0718876849291332,
    "random_rewards": -1.820585632981706,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0095339783590935,
    "equal_rewards": -2.072346605513168,
    "random_rewards": -1.5110717079607388,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0193875901250955,
    "equal_rewards": -2.0746429103602964,
    "random_rewards": -1.3498828402665786,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0091871328423077,
    "equal_rewards": -2.0488690215416265,
    "random_rewards": -2.1274444843950473,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9990889818264206,
    "equal_rewards": -2.051759077967605,
    "random_rewards": -1.9238506780051834,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016049001828647,
    "equal_rewards": -2.0665647286693507,
    "random_rewards": -1.9799705585678775,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.02749205094001,
    "equal_rewards": -2.040205562245525,
    "random_rewards": -1.6853497053204687,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0244987627195106,
    "equal_rewards": -2.0106556368272495,
    "random_rewards": -1.5798378810762022,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9864146084579555,
    "equal_rewards": -2.0488588162074963,
    "random_rewards": -1.52644579151894,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.030549285032067,
    "equal_rewards": -2.045811113916816,
    "random_rewards": -1.4825818435096467,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9860701658241084,
    "equal_rewards": -2.038796189936804,
    "random_rewards": -1.8346500910822803,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9945279779422393,
    "equal_rewards": -2.0318747613522956,
    "random_rewards": -1.91941561170708,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9937902616949876,
    "equal_rewards": -2.0438236372731255,
    "random_rewards": -2.1070496777006813,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0322373411469745,
    "equal_rewards": -2.057120509238347,
    "random_rewards": -2.083222805499543,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.055237582124063,
    "equal_rewards": -2.039558238800096,
    "random_rewards": -1.6166755217924431,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010044216247153,
    "equal_rewards": -2.0557871600922883,
    "random_rewards": -2.2598875225644943,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.031248480102707,
    "equal_rewards": -2.063797739229453,
    "random_rewards": -0.8911461019851363,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.006738242593821,
    "equal_rewards": -2.0648844068202425,
    "random_rewards": -1.6992697445226312,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.063602737324581,
    "equal_rewards": -2.021095059506282,
    "random_rewards": -1.0211413678191337,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0365925010875165,
    "equal_rewards": -2.0589024062651267,
    "random_rewards": -1.6370620573642856,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0093543232014435,
    "equal_rewards": -2.064685339050973,
    "random_rewards": -2.1441230755888023,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.056185747492262,
    "equal_rewards": -2.019625877822132,
    "random_rewards": -2.0529006131534624,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0352803087274105,
    "equal_rewards": -2.0339831683429836,
    "random_rewards": -0.7457672027727142,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0179623042317796,
    "equal_rewards": -2.0710640039613324,
    "random_rewards": -1.6501885437905954,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0362092970176198,
    "equal_rewards": -2.0273935373832117,
    "random_rewards": -1.0370583515456322,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0004582586509554,
    "equal_rewards": -2.0413407249265636,
    "random_rewards": -1.508749671488087,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.02631749539933,
    "equal_rewards": -2.024459925828471,
    "random_rewards": -2.6845315537130383,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9942071412207842,
    "equal_rewards": -2.046666249757235,
    "random_rewards": -1.9176972017429188,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0050593001202976,
    "equal_rewards": -2.0604872199902955,
    "random_rewards": -1.2089486111125414,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0034566529370537,
    "equal_rewards": -2.038506402499535,
    "random_rewards": -1.6264950723031806,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9840449595892657,
    "equal_rewards": -2.0394584147694323,
    "random_rewards": -2.5297427914120534,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010509797490765,
    "equal_rewards": -2.0535689151958003,
    "random_rewards": -1.382327436836694,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9957149347964516,
    "equal_rewards": -2.0428914617015796,
    "random_rewards": -1.6495749626126441,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9918853009513895,
    "equal_rewards": -2.044723488320159,
    "random_rewards": -2.3849432107708353,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9911710723733977,
    "equal_rewards": -2.047873452638324,
    "random_rewards": -1.7981327876824307,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000040577734756,
    "equal_rewards": -2.0371380168648496,
    "random_rewards": -1.9518304454163504,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.015232229707542,
    "equal_rewards": -2.04212225934144,
    "random_rewards": -1.0685168495838666,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0119023007605135,
    "equal_rewards": -2.0649888112144374,
    "random_rewards": -1.3679768258614744,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0185126673164357,
    "equal_rewards": -2.0383525396879736,
    "random_rewards": -2.990151358059896,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.993139329171199,
    "equal_rewards": -2.0047763314040834,
    "random_rewards": -2.0226238202092666,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9807979607087054,
    "equal_rewards": -2.034885903817816,
    "random_rewards": -1.3400468147092934,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.006587587526705,
    "equal_rewards": -2.061662668048422,
    "random_rewards": -1.5106779867463247,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.037560860818012,
    "equal_rewards": -2.030611747815592,
    "random_rewards": -0.9032113316754057,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0326989313856836,
    "equal_rewards": -2.0576835457751645,
    "random_rewards": -2.6953491329748,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0471809587530676,
    "equal_rewards": -2.0347267914295877,
    "random_rewards": -2.215905397148926,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0162985134835685,
    "equal_rewards": -2.049311178156459,
    "random_rewards": -1.6827879719406829,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0350242982903715,
    "equal_rewards": -2.0548834609615647,
    "random_rewards": -2.117919815801822,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0091681447747214,
    "equal_rewards": -2.072792886588224,
    "random_rewards": -3.0411367100627924,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0304045899010505,
    "equal_rewards": -2.057008038988141,
    "random_rewards": -2.384777827743686,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.053006589570316,
    "equal_rewards": -2.0372826278555225,
    "random_rewards": -1.9560765022288908,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010870363055503,
    "equal_rewards": -2.066495835929137,
    "random_rewards": -1.9512992594158076,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.001356802757413,
    "equal_rewards": -2.04141190342911,
    "random_rewards": -0.873694328478238,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0224104238806953,
    "equal_rewards": -2.007204488330736,
    "random_rewards": -1.4448037205845021,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0078231310105807,
    "equal_rewards": -2.0607566056394515,
    "random_rewards": -1.3595652582637763,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0074113288381703,
    "equal_rewards": -2.065294921016637,
    "random_rewards": -1.946881323279146,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0120685203945667,
    "equal_rewards": -2.0319903364237732,
    "random_rewards": -1.6653840116612852,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0166995337025293,
    "equal_rewards": -2.006862842453966,
    "random_rewards": -2.3398604707819137,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.026371037797528,
    "equal_rewards": -2.0511496254801216,
    "random_rewards": -1.4802852793113987,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0522037962260935,
    "equal_rewards": -2.027233336817242,
    "random_rewards": -1.906746960261573,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9968517813098714,
    "equal_rewards": -2.057168482452695,
    "random_rewards": -1.0689886650712521,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0088306039866977,
    "equal_rewards": -2.060858311097392,
    "random_rewards": -1.1836265588353028,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0362988192813676,
    "equal_rewards": -2.057926717697639,
    "random_rewards": -1.6693205396254125,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.005317239485824,
    "equal_rewards": -2.072692637410957,
    "random_rewards": -2.1252774057546477,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0486008132849816,
    "equal_rewards": -2.033523162829119,
    "random_rewards": -1.6420575503523382,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.059164259704535,
    "equal_rewards": -2.0374251590990644,
    "random_rewards": -2.069695015784073,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0129701154930517,
    "equal_rewards": -2.076009613319998,
    "random_rewards": -2.11479727278329,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0257871110962724,
    "equal_rewards": -2.0462671980040845,
    "random_rewards": -1.9585757990923658,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0363894361685726,
    "equal_rewards": -2.0557642224415895,
    "random_rewards": -1.2041724743791784,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0165760776774464,
    "equal_rewards": -2.0770479161673285,
    "random_rewards": -1.1858258701386428,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.015899198191769,
    "equal_rewards": -2.0687995648177693,
    "random_rewards": -2.293589873769406,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0361556964965097,
    "equal_rewards": -2.0579393308142873,
    "random_rewards": -2.4314515885245225,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.049492321988421,
    "equal_rewards": -2.0204854329737056,
    "random_rewards": -2.6661769349022992,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004584191037896,
    "equal_rewards": -2.0222896033119726,
    "random_rewards": -1.6347404623265511,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016938780790812,
    "equal_rewards": -2.044130388406453,
    "random_rewards": -1.8180676647164185,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.012269385782233,
    "equal_rewards": -2.0695389796701,
    "random_rewards": -1.6779462452645268,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010545863804081,
    "equal_rewards": -2.075721670948359,
    "random_rewards": -1.5373337127673965,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.034909069117946,
    "equal_rewards": -2.050840462721417,
    "random_rewards": -2.2430129344503285,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.997648683280273,
    "equal_rewards": -2.050842966951344,
    "random_rewards": -1.6664671574932004,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.033235838338537,
    "equal_rewards": -2.058164079698326,
    "random_rewards": -2.2130509133240412,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0269754801893685,
    "equal_rewards": -2.0514724559607505,
    "random_rewards": -1.944092432999245,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.001183444491267,
    "equal_rewards": -2.046105630196937,
    "random_rewards": -2.261974341015916,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9952291742884423,
    "equal_rewards": -2.047964397799463,
    "random_rewards": -2.8543556490051074,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0515850859550007,
    "equal_rewards": -2.0181346245356355,
    "random_rewards": -2.03857602629426,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.995221236766988,
    "equal_rewards": -2.0507700633558796,
    "random_rewards": -2.1167355776716916,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9902763624820567,
    "equal_rewards": -2.0405831755541977,
    "random_rewards": -1.3545714421584536,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.981030150735749,
    "equal_rewards": -2.0299180863173545,
    "random_rewards": -1.0086379996530987,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9941220945241804,
    "equal_rewards": -2.0472210359312966,
    "random_rewards": -1.3169841186793472,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9979396771279796,
    "equal_rewards": -2.039666131679458,
    "random_rewards": -2.062119346315653,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0187457130509796,
    "equal_rewards": -2.0418115894254183,
    "random_rewards": -1.929044449917334,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.01596196849751,
    "equal_rewards": -2.063891072984336,
    "random_rewards": -2.438565963269565,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0432689733775335,
    "equal_rewards": -2.027519029610418,
    "random_rewards": -1.9433530189611898,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.972587445266425,
    "equal_rewards": -2.0380070379907775,
    "random_rewards": -1.6106632761655888,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.031050339664704,
    "equal_rewards": -2.0213446698293254,
    "random_rewards": -1.3448408904763423,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.03249348345186,
    "equal_rewards": -2.014625327422872,
    "random_rewards": -2.0674823562846187,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0165462449898666,
    "equal_rewards": -2.0413903786923977,
    "random_rewards": -1.772851073037075,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0575419707869673,
    "equal_rewards": -2.0394323634033666,
    "random_rewards": -1.9312788218205474,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0376435615887942,
    "equal_rewards": -2.0625624688249955,
    "random_rewards": -1.830543125944349,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0714994328309135,
    "equal_rewards": -2.040705697185159,
    "random_rewards": -1.773591774698679,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0195111282607128,
    "equal_rewards": -2.082114614614106,
    "random_rewards": -1.2288122544123208,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013936129313014,
    "equal_rewards": -2.0670721246414807,
    "random_rewards": -1.7987450929028377,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0305129098712413,
    "equal_rewards": -2.055384175596826,
    "random_rewards": -1.77354475150984,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0120159664389,
    "equal_rewards": -2.0651284245253514,
    "random_rewards": -2.2448264936982776,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0153510485426946,
    "equal_rewards": -2.0609825995935176,
    "random_rewards": -2.5484234302404833,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9990256073024921,
    "equal_rewards": -2.0616175270691035,
    "random_rewards": -1.7921796559716965,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.014392704674491,
    "equal_rewards": -2.068041875771923,
    "random_rewards": -2.1259868361693277,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0231694379613425,
    "equal_rewards": -2.0499898764915523,
    "random_rewards": -1.0725126083344423,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.04925109822232,
    "equal_rewards": -2.0354893587600107,
    "random_rewards": -1.4898516337619188,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011429665792667,
    "equal_rewards": -2.0712105567655406,
    "random_rewards": -1.04497657699775,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0192395111286716,
    "equal_rewards": -2.0698707336526225,
    "random_rewards": -1.6886643647196473,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0530390049533196,
    "equal_rewards": -2.0373238373831963,
    "random_rewards": -1.7989582646419056,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.028805383880749,
    "equal_rewards": -2.053764417138162,
    "random_rewards": -1.6683584383376882,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.050412840149095,
    "equal_rewards": -2.035565330342905,
    "random_rewards": -2.067811713234294,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0518905124225504,
    "equal_rewards": -2.032641775154464,
    "random_rewards": -2.100814624577758,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0321370877322043,
    "equal_rewards": -2.0579964607253722,
    "random_rewards": -2.3944057890465738,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.009604034933233,
    "equal_rewards": -2.0647186522885255,
    "random_rewards": -2.2971701334510053,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0112870089924604,
    "equal_rewards": -2.064187461400582,
    "random_rewards": -1.4865517403692934,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010101642321043,
    "equal_rewards": -2.0634727588146773,
    "random_rewards": -1.1774131438758155,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0057574734386034,
    "equal_rewards": -2.0594081796307533,
    "random_rewards": -0.7460994167205133,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0201557008047972,
    "equal_rewards": -2.052777834233342,
    "random_rewards": -2.0645492654569386,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.028183698994043,
    "equal_rewards": -2.049749109007421,
    "random_rewards": -2.133311827222707,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.015576133276908,
    "equal_rewards": -2.056770170406548,
    "random_rewards": -2.0821697472087872,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.037582638169085,
    "equal_rewards": -2.0040558864062907,
    "random_rewards": -2.9402047015604227,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.948885991752,
    "equal_rewards": -2.0022993301986673,
    "random_rewards": -1.7949767581966594,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000754984806968,
    "equal_rewards": -2.056490674007391,
    "random_rewards": -2.405221595764869,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.003943137750751,
    "equal_rewards": -2.065814400147776,
    "random_rewards": -1.4955353308907195,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.943991228196412,
    "equal_rewards": -1.9965100805636307,
    "random_rewards": -1.5653443440154162,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9010465864921242,
    "equal_rewards": -1.936085347726326,
    "random_rewards": -1.8425888032412865,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9548725218608796,
    "equal_rewards": -2.0078904531720734,
    "random_rewards": -1.6398717980900437,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9846500083655134,
    "equal_rewards": -2.03251951808313,
    "random_rewards": -1.9759258207697756,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.005263056947408,
    "equal_rewards": -2.050792631273135,
    "random_rewards": -2.5341225841882116,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0137515325947586,
    "equal_rewards": -2.0667360226145393,
    "random_rewards": -2.7301369755494784,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.026875009301233,
    "equal_rewards": -2.053488731054964,
    "random_rewards": -1.350845164740178,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0077580447424577,
    "equal_rewards": -2.058315352504336,
    "random_rewards": -2.425039444583013,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0622027774213905,
    "equal_rewards": -2.0375218184994672,
    "random_rewards": -1.632307437288264,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0218418872776747,
    "equal_rewards": -2.0374521379381982,
    "random_rewards": -1.2022548277930192,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0038677670386273,
    "equal_rewards": -2.0281729553271686,
    "random_rewards": -0.898308562011314,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007904626428643,
    "equal_rewards": -2.0632511024023485,
    "random_rewards": -1.02616181874413,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9980489650811977,
    "equal_rewards": -2.042791347589146,
    "random_rewards": -1.0550229657447687,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.020108730070798,
    "equal_rewards": -2.0372693669294346,
    "random_rewards": -1.319726385609377,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.014270180654549,
    "equal_rewards": -2.0671180988387494,
    "random_rewards": -1.9719807112366445,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.038447432188939,
    "equal_rewards": -2.0172184052341002,
    "random_rewards": -1.635600196834131,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9790155351396446,
    "equal_rewards": -2.0111656025511406,
    "random_rewards": -2.3395507927096943,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9897985815340793,
    "equal_rewards": -2.0390745590291797,
    "random_rewards": -1.7677005218929498,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0349782569908834,
    "equal_rewards": -2.0567011556129966,
    "random_rewards": -0.7593070081141294,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0184980056098256,
    "equal_rewards": -2.067072834192299,
    "random_rewards": -1.9800872913976706,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.008742457729384,
    "equal_rewards": -2.0543507730217168,
    "random_rewards": -2.382921526768019,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010239594900341,
    "equal_rewards": -2.064128246518732,
    "random_rewards": -1.3615008267767084,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0020012342902307,
    "equal_rewards": -2.0620037456524667,
    "random_rewards": -0.9113801410004851,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.023340033695427,
    "equal_rewards": -2.0516241251626006,
    "random_rewards": -1.9565588811149472,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9505338617866932,
    "equal_rewards": -1.967043381816541,
    "random_rewards": -1.0132654935321437,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9460772385660872,
    "equal_rewards": -1.9726259983109156,
    "random_rewards": -2.0267289874479437,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.006374831924473,
    "equal_rewards": -2.0580287774400956,
    "random_rewards": -2.8600430229193003,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0003189390242944,
    "equal_rewards": -2.04016408306506,
    "random_rewards": -2.0762860209070055,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.012103346102729,
    "equal_rewards": -2.0398657203931454,
    "random_rewards": -2.2232606746492394,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0548767712785017,
    "equal_rewards": -2.0297755042936183,
    "random_rewards": -1.2030187737169762,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.034176010335595,
    "equal_rewards": -2.05729888231894,
    "random_rewards": -1.9835992470295871,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.019653357032279,
    "equal_rewards": -2.0522211191586073,
    "random_rewards": -2.854628361180535,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013772703708289,
    "equal_rewards": -2.0660213867920607,
    "random_rewards": -1.9885222690443312,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0140778386166693,
    "equal_rewards": -2.064426636710361,
    "random_rewards": -2.704093010098791,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.008353219290758,
    "equal_rewards": -2.0708569246698962,
    "random_rewards": -0.9151884064502478,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9616300827707653,
    "equal_rewards": -1.9827087124432776,
    "random_rewards": -2.1802989693242365,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9336092537102947,
    "equal_rewards": -1.995828765948699,
    "random_rewards": -2.6286525210056038,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0092612054835683,
    "equal_rewards": -2.073300444814546,
    "random_rewards": -1.4858144632103523,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.022754084163198,
    "equal_rewards": -2.0013634586718645,
    "random_rewards": -1.4300289837375595,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.7302762043954725,
    "equal_rewards": -1.690220452230958,
    "random_rewards": -1.9932185465880725,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.442874036224253,
    "equal_rewards": -1.504291595398732,
    "random_rewards": -1.332212965280939,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8081579898272513,
    "equal_rewards": -1.8104544753319551,
    "random_rewards": -1.7311047382902252,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.033373033149135,
    "equal_rewards": -2.0116638679615564,
    "random_rewards": -2.1828433039211825,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000250369285589,
    "equal_rewards": -2.0193609754182305,
    "random_rewards": -1.9283032071657777,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9829489364673347,
    "equal_rewards": -2.0351350056537325,
    "random_rewards": -1.9694045257213186,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.973988327596087,
    "equal_rewards": -2.0243182556286956,
    "random_rewards": -3.110537807429459,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.957911032503116,
    "equal_rewards": -2.0119464448993254,
    "random_rewards": -0.4416467805876567,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.96229248875637,
    "equal_rewards": -2.0134747584261246,
    "random_rewards": -1.4761709730853116,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9715462876816139,
    "equal_rewards": -1.9924736278341886,
    "random_rewards": -1.9166959127819636,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9422990675472145,
    "equal_rewards": -1.9693183001311636,
    "random_rewards": -1.9881105407562183,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0125889775446395,
    "equal_rewards": -1.9834148827007467,
    "random_rewards": -2.0277868466238917,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0103803351505753,
    "equal_rewards": -2.0724329136575297,
    "random_rewards": -1.981259585632852,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.017851129159539,
    "equal_rewards": -2.0705236138957517,
    "random_rewards": -2.136729149916272,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.026534431635948,
    "equal_rewards": -2.0324863583430433,
    "random_rewards": -2.9749205906800746,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9895661202965038,
    "equal_rewards": -2.035253081843767,
    "random_rewards": -1.9584537493271774,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0138182268998763,
    "equal_rewards": -2.0314085877401404,
    "random_rewards": -2.3701395700049894,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9775471998145906,
    "equal_rewards": -2.0443332086579513,
    "random_rewards": -1.3547632303021437,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0070591160866567,
    "equal_rewards": -2.064722955172347,
    "random_rewards": -2.1080600040160697,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007841547680718,
    "equal_rewards": -2.065905143046567,
    "random_rewards": -1.3457251484359873,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9893348821577543,
    "equal_rewards": -2.003452545391426,
    "random_rewards": -2.186154550501994,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004430565903013,
    "equal_rewards": -1.9916045180950173,
    "random_rewards": -2.6149762342685516,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9453277292891094,
    "equal_rewards": -1.999954654565316,
    "random_rewards": -1.472690616013625,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9891259356229563,
    "equal_rewards": -2.0090938656720096,
    "random_rewards": -1.2986337868510982,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.069549836336092,
    "equal_rewards": -2.029556389636589,
    "random_rewards": -1.1927563314280225,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0510367243680814,
    "equal_rewards": -2.0350786560605147,
    "random_rewards": -1.340173749113022,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0441520928998926,
    "equal_rewards": -2.0352588493574157,
    "random_rewards": -2.3591847003181208,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.023940922162887,
    "equal_rewards": -1.9986865179569262,
    "random_rewards": -2.209317315596727,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9674045890345182,
    "equal_rewards": -2.0201416228994464,
    "random_rewards": -1.7368736984387128,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9625495310109484,
    "equal_rewards": -2.0131534112314786,
    "random_rewards": -1.9482931998371629,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007336882809083,
    "equal_rewards": -2.028453724716883,
    "random_rewards": -1.6621623008875244,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0097711530677564,
    "equal_rewards": -2.06575819994214,
    "random_rewards": -1.777187508771434,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.001452868563965,
    "equal_rewards": -2.066296990448704,
    "random_rewards": -1.4815882859034368,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.038299653114681,
    "equal_rewards": -2.0580327148991664,
    "random_rewards": -1.3626128361077803,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9509461954656744,
    "equal_rewards": -2.014628963608141,
    "random_rewards": -1.4600641920832336,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9785924861468498,
    "equal_rewards": -2.027349404247822,
    "random_rewards": -2.402865328388194,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.012204548395593,
    "equal_rewards": -2.037714867423034,
    "random_rewards": -2.212652789583931,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9491851943367802,
    "equal_rewards": -2.0148124575948145,
    "random_rewards": -1.95359259889258,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9524160286355372,
    "equal_rewards": -2.003977637561992,
    "random_rewards": -2.93222340463428,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.995189819664168,
    "equal_rewards": -2.012606699755232,
    "random_rewards": -2.032459281467392,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9873342598426724,
    "equal_rewards": -2.0447348515085073,
    "random_rewards": -1.8328236892544312,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9726448924837288,
    "equal_rewards": -2.0234563079192993,
    "random_rewards": -1.341446005229927,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9951308917621713,
    "equal_rewards": -2.0217915197143412,
    "random_rewards": -1.9268100653372024,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9851553684212448,
    "equal_rewards": -2.038193102136696,
    "random_rewards": -1.9474004885429956,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.991060304214563,
    "equal_rewards": -2.0484042960248368,
    "random_rewards": -2.238149718524869,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.032051063802709,
    "equal_rewards": -2.0160603631079335,
    "random_rewards": -2.377209627028031,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0447644943138314,
    "equal_rewards": -2.020105294071178,
    "random_rewards": -2.356419415994753,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9998077158371381,
    "equal_rewards": -2.064537155825933,
    "random_rewards": -0.9206187095130189,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0020294039151043,
    "equal_rewards": -2.035070225158063,
    "random_rewards": -1.9063142846774417,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9827204898377773,
    "equal_rewards": -2.036558367858387,
    "random_rewards": -1.6761570471809124,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0126060531574868,
    "equal_rewards": -2.0412223156316642,
    "random_rewards": -1.52323945624158,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.024194001447291,
    "equal_rewards": -2.0113214247467597,
    "random_rewards": -1.896888210373333,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.006027640943256,
    "equal_rewards": -2.0184487962748796,
    "random_rewards": -1.9335860079870844,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9782718948788318,
    "equal_rewards": -2.031174392704439,
    "random_rewards": -1.8878704614834692,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0011559602516282,
    "equal_rewards": -2.0505408634636852,
    "random_rewards": -1.9673981528640458,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.012368953426541,
    "equal_rewards": -1.9861071535346109,
    "random_rewards": -2.0695458956794837,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9383251787072304,
    "equal_rewards": -1.983822949076353,
    "random_rewards": -2.621188259263055,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0031431581829127,
    "equal_rewards": -2.0556077794813112,
    "random_rewards": -2.2748734753162303,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9522424920655617,
    "equal_rewards": -1.9986088185030058,
    "random_rewards": -1.724332837855798,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9793553527948193,
    "equal_rewards": -2.0301683307028027,
    "random_rewards": -1.485836345025363,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9819072171657908,
    "equal_rewards": -1.9640697633431188,
    "random_rewards": -2.1486074103713713,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.997358971906874,
    "equal_rewards": -2.0349309785638354,
    "random_rewards": -1.6068202366577782,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.905845839644114,
    "equal_rewards": -1.943603552255924,
    "random_rewards": -2.538148382314307,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9345319357146502,
    "equal_rewards": -1.9557699778515092,
    "random_rewards": -1.4117041878738865,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9715851520262904,
    "equal_rewards": -2.032344927293036,
    "random_rewards": -1.7466102133949393,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9902904193653095,
    "equal_rewards": -2.031980106827814,
    "random_rewards": -1.5032037226076362,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0032535478048876,
    "equal_rewards": -2.0257896263855546,
    "random_rewards": -1.6227736145770395,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.991622396156008,
    "equal_rewards": -2.0493561506061404,
    "random_rewards": -1.5230470482466436,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0284302125728444,
    "equal_rewards": -2.053875869804799,
    "random_rewards": -1.487971908965899,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.989304418549644,
    "equal_rewards": -2.014033039371193,
    "random_rewards": -2.035259112010892,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0107415613047905,
    "equal_rewards": -2.032327335141578,
    "random_rewards": -1.6206687089173828,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004059753950391,
    "equal_rewards": -2.0717167721043923,
    "random_rewards": -2.7341848951833105,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0435927648097256,
    "equal_rewards": -2.0637209103195415,
    "random_rewards": -2.228325143911733,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.047443655179295,
    "equal_rewards": -2.0283428615685635,
    "random_rewards": -1.3092380609366074,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9584111671407562,
    "equal_rewards": -1.9808620125113179,
    "random_rewards": -2.343045573883844,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9380621548845762,
    "equal_rewards": -1.992173217935009,
    "random_rewards": -1.0429511100512565,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0181663931853904,
    "equal_rewards": -2.038839604390581,
    "random_rewards": -1.947138007727013,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9683649606617113,
    "equal_rewards": -1.9849852194913435,
    "random_rewards": -1.1616085715044333,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9966865174117698,
    "equal_rewards": -1.9826826389142815,
    "random_rewards": -1.4679971639293925,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9849859458989008,
    "equal_rewards": -2.045054900058478,
    "random_rewards": -2.566028084270103,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9239692784726152,
    "equal_rewards": -1.9594302377419264,
    "random_rewards": -2.030108617362366,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8296130272555367,
    "equal_rewards": -1.8463597305944321,
    "random_rewards": -1.925739514066213,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9128202909550538,
    "equal_rewards": -1.9434683783781375,
    "random_rewards": -1.1178560577225771,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9878856939567981,
    "equal_rewards": -2.0216581288552997,
    "random_rewards": -2.110655462203492,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.942222859616488,
    "equal_rewards": -2.0009543534645555,
    "random_rewards": -1.3241154153661956,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.991571442315669,
    "equal_rewards": -2.043806702559971,
    "random_rewards": -1.0452064889526516,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9710413855948556,
    "equal_rewards": -1.9945310335032258,
    "random_rewards": -1.625007634332073,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.96684849011822,
    "equal_rewards": -2.0171588311873205,
    "random_rewards": -1.0361628634552007,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9679133811030531,
    "equal_rewards": -1.9461729525313818,
    "random_rewards": -1.4414803882071217,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9815111886581218,
    "equal_rewards": -2.0235906527452454,
    "random_rewards": -2.0558110267226146,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.031689554490014,
    "equal_rewards": -2.0155627158950717,
    "random_rewards": -1.7580845016665643,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9664825458855244,
    "equal_rewards": -1.98425411289828,
    "random_rewards": -1.5749976022763608,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.982710360792992,
    "equal_rewards": -1.9628112511631066,
    "random_rewards": -1.4702755178861422,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9024455272885157,
    "equal_rewards": -1.9130299432870288,
    "random_rewards": -1.5740420323137512,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8939568693960926,
    "equal_rewards": -1.9450483169981196,
    "random_rewards": -1.8397316331182898,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9977969027421199,
    "equal_rewards": -1.9842425796344183,
    "random_rewards": -2.022253747582936,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9767820816344401,
    "equal_rewards": -2.0253017904652975,
    "random_rewards": -2.2403903227006388,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9353807497356623,
    "equal_rewards": -1.9934579652155433,
    "random_rewards": -2.0575859824793747,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9129822576704791,
    "equal_rewards": -1.9537442743462985,
    "random_rewards": -2.2778525369509643,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9217945769674287,
    "equal_rewards": -1.9455086977088145,
    "random_rewards": -1.4177869044606566,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9292686053311192,
    "equal_rewards": -1.9410818257130464,
    "random_rewards": -1.5284715819729908,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9199087236576453,
    "equal_rewards": -1.9686900364572515,
    "random_rewards": -1.889745896746699,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9607308945287694,
    "equal_rewards": -1.9832124915416496,
    "random_rewards": -1.308399460617876,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9686894370381545,
    "equal_rewards": -1.9913198681662398,
    "random_rewards": -1.9236235968582238,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0253125512279118,
    "equal_rewards": -1.9961165066932165,
    "random_rewards": -1.331770017167807,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9898607223063431,
    "equal_rewards": -1.9812587256613339,
    "random_rewards": -1.9046971618164368,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011277142444801,
    "equal_rewards": -1.985524592421509,
    "random_rewards": -2.1545674084923987,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9693663014337557,
    "equal_rewards": -1.9795430042478754,
    "random_rewards": -2.6132096389763735,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9593434169051491,
    "equal_rewards": -1.993283888753413,
    "random_rewards": -0.8825545087800826,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9482295918581618,
    "equal_rewards": -1.9658548566173843,
    "random_rewards": -1.8715425405790804,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0106337590041625,
    "equal_rewards": -1.984211521747052,
    "random_rewards": -1.2951365453849053,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.946565774756734,
    "equal_rewards": -1.9987882652549194,
    "random_rewards": -1.5634484683123764,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9919112520093096,
    "equal_rewards": -1.9579856563663223,
    "random_rewards": -1.0063303084120891,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9789058688060228,
    "equal_rewards": -1.98252422210843,
    "random_rewards": -2.170929554336065,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9492896867663565,
    "equal_rewards": -1.9601634129512484,
    "random_rewards": -1.7332817498955149,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9311541532600973,
    "equal_rewards": -1.9604664084580063,
    "random_rewards": -1.9730843447393176,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9693683468374132,
    "equal_rewards": -1.9874986562507666,
    "random_rewards": -2.2013338002607004,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.997770686982021,
    "equal_rewards": -1.9922087718867434,
    "random_rewards": -1.4912993921461795,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.02075942172799,
    "equal_rewards": -1.9920166693083328,
    "random_rewards": -2.75816150966366,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9604342582178698,
    "equal_rewards": -1.9944651983151203,
    "random_rewards": -0.7434920806943217,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9799275507043024,
    "equal_rewards": -2.0056880231900442,
    "random_rewards": -1.6150448956748562,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.017655227641431,
    "equal_rewards": -2.012890792257939,
    "random_rewards": -2.651124458095822,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9983069380094989,
    "equal_rewards": -2.0065247046086605,
    "random_rewards": -1.306279045820425,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007146348550359,
    "equal_rewards": -1.9626358445494885,
    "random_rewards": -2.5669386043441795,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.977372935453971,
    "equal_rewards": -2.0093632067702045,
    "random_rewards": -1.6542093323793483,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.977354535990918,
    "equal_rewards": -1.960368609709617,
    "random_rewards": -1.1810752045168313,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.968872888905962,
    "equal_rewards": -1.992763856073346,
    "random_rewards": -2.0631957739865077,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9610767073966349,
    "equal_rewards": -1.9916022949382157,
    "random_rewards": -2.0367759768110045,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9902390175132179,
    "equal_rewards": -1.9522403499602878,
    "random_rewards": -1.4306343823860903,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9642610542467167,
    "equal_rewards": -1.982592503045003,
    "random_rewards": -1.2984169850341702,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9867863383855575,
    "equal_rewards": -1.9830224091914967,
    "random_rewards": -1.9188468502895075,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9448441671777361,
    "equal_rewards": -2.0000720662363034,
    "random_rewards": -2.650629467903567,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9568615797009294,
    "equal_rewards": -1.963544047640983,
    "random_rewards": -1.1488826719618876,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9575658794197477,
    "equal_rewards": -1.9166626032658074,
    "random_rewards": -1.9487744967316174,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.923778706060522,
    "equal_rewards": -1.961819398818303,
    "random_rewards": -2.274449806165998,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9671191225999296,
    "equal_rewards": -1.9830789327420106,
    "random_rewards": -2.3229816066461564,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9759515818222537,
    "equal_rewards": -2.0134355218024003,
    "random_rewards": -1.4485629449493536,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9368023582648957,
    "equal_rewards": -1.893891670143176,
    "random_rewards": -1.78630943291237,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8453079095562184,
    "equal_rewards": -1.8740510419479819,
    "random_rewards": -2.606843850154815,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9013639642359217,
    "equal_rewards": -1.9067563764828266,
    "random_rewards": -1.4008682295620067,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0003242804986936,
    "equal_rewards": -1.97992960808129,
    "random_rewards": -2.157909520256712,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9264277783261199,
    "equal_rewards": -1.974061759531539,
    "random_rewards": -1.6042514102701857,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9578567351924199,
    "equal_rewards": -1.925068206321975,
    "random_rewards": -1.4363223548936368,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9087176610249952,
    "equal_rewards": -1.9248963576955598,
    "random_rewards": -1.29268281050854,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9416055306290483,
    "equal_rewards": -1.9503767367728988,
    "random_rewards": -1.7403508142427575,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9766268902226956,
    "equal_rewards": -2.003936411675623,
    "random_rewards": -1.3190139070810705,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9895844184077855,
    "equal_rewards": -2.037246127739979,
    "random_rewards": -2.218267015827009,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.034477907751579,
    "equal_rewards": -2.0140717847539213,
    "random_rewards": -0.5901765340664997,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.022849173907437,
    "equal_rewards": -1.9875844678731345,
    "random_rewards": -1.9037912558666163,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0049857609533115,
    "equal_rewards": -1.993633791841149,
    "random_rewards": -1.2886427502090347,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9688183778172827,
    "equal_rewards": -2.019186449487825,
    "random_rewards": -0.5831664707042965,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9645442794829457,
    "equal_rewards": -1.992807248987125,
    "random_rewards": -1.563739473855997,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9150569438131657,
    "equal_rewards": -1.890181093237219,
    "random_rewards": -2.6396990744310136,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8075170855955789,
    "equal_rewards": -1.8497010245824175,
    "random_rewards": -1.6540993894749456,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8872352684654459,
    "equal_rewards": -1.9369382401917554,
    "random_rewards": -1.8772256648447612,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.918418822015824,
    "equal_rewards": -1.951682912784284,
    "random_rewards": -2.1092006622213053,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8996176317127582,
    "equal_rewards": -1.8943925463275622,
    "random_rewards": -1.949756896634927,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9847386322535616,
    "equal_rewards": -1.9525639245697868,
    "random_rewards": -2.5521990547746816,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9165743280426562,
    "equal_rewards": -1.919524416861623,
    "random_rewards": -1.9836017636717798,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9106505815410615,
    "equal_rewards": -1.89393614053817,
    "random_rewards": -1.6723701915854465,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8976324555742885,
    "equal_rewards": -1.9666839511314844,
    "random_rewards": -2.1444043357747145,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9562766917537053,
    "equal_rewards": -1.9149269167831955,
    "random_rewards": -2.3849234952182354,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9412899018104155,
    "equal_rewards": -1.9653321176215754,
    "random_rewards": -2.87604726002973,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9850688844597548,
    "equal_rewards": -2.0117554787533645,
    "random_rewards": -0.5968018486430171,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.026203786586297,
    "equal_rewards": -2.0034017370176382,
    "random_rewards": -1.7385274475060495,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9852177104804203,
    "equal_rewards": -1.993369369596921,
    "random_rewards": -1.879217094848578,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.942202318133004,
    "equal_rewards": -2.01273212964256,
    "random_rewards": -2.229243246309374,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9410995952656434,
    "equal_rewards": -1.96082219917679,
    "random_rewards": -1.273971871659127,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9692452779928624,
    "equal_rewards": -1.9488161448010428,
    "random_rewards": -1.7268620088486664,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9977870803241946,
    "equal_rewards": -2.0007049335600975,
    "random_rewards": -1.8900955705458289,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0010986315887895,
    "equal_rewards": -1.9568686430886222,
    "random_rewards": -1.4575399185414588,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9817795510812277,
    "equal_rewards": -2.0189961791815954,
    "random_rewards": -1.2863898587230551,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0006005796213655,
    "equal_rewards": -2.027874436012787,
    "random_rewards": -2.201928591460125,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9608497377863592,
    "equal_rewards": -1.9958696029863239,
    "random_rewards": -2.652899587475112,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9790455358893133,
    "equal_rewards": -1.9486545345124986,
    "random_rewards": -2.1139643701799042,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9422978116809242,
    "equal_rewards": -1.9303302068351038,
    "random_rewards": -0.835860957242351,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9738694178588043,
    "equal_rewards": -2.004667064968371,
    "random_rewards": -2.1783176260799024,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9790909359679731,
    "equal_rewards": -2.001302662471116,
    "random_rewards": -2.796416915292852,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9366494730446544,
    "equal_rewards": -1.9788526863259204,
    "random_rewards": -2.888475661322599,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9928129174175748,
    "equal_rewards": -1.963223843831484,
    "random_rewards": -1.758541301327965,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9906423454355464,
    "equal_rewards": -1.9567713149703927,
    "random_rewards": -0.7175916900466226,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9143957370106028,
    "equal_rewards": -1.9719570819708547,
    "random_rewards": -1.1469591411331717,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9640804833515793,
    "equal_rewards": -1.97983464076989,
    "random_rewards": -2.3180155261161985,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9943554103795906,
    "equal_rewards": -2.0106861132529184,
    "random_rewards": -1.747443215867031,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0025422835239577,
    "equal_rewards": -1.9916732339928984,
    "random_rewards": -1.1476667615379108,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9645402310537763,
    "equal_rewards": -2.018679767092519,
    "random_rewards": -1.2114846217529966,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0082093579986333,
    "equal_rewards": -1.987372570249299,
    "random_rewards": -2.458253169219848,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9435487750600369,
    "equal_rewards": -1.9895885883313684,
    "random_rewards": -1.0028552594017892,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.99892113564926,
    "equal_rewards": -2.027249243122238,
    "random_rewards": -2.966949154214104,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0310829288401275,
    "equal_rewards": -2.003138587251285,
    "random_rewards": -1.9338612750523216,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9410288729681398,
    "equal_rewards": -1.976037384206141,
    "random_rewards": -2.3007965318889294,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9726749320978745,
    "equal_rewards": -1.9564944967007114,
    "random_rewards": -2.5809885949124274,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9840831763492153,
    "equal_rewards": -2.023361099975622,
    "random_rewards": -2.100447521406009,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9783983648854684,
    "equal_rewards": -1.931762691653225,
    "random_rewards": -1.9664894656673555,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.908742156876924,
    "equal_rewards": -1.9331200232351344,
    "random_rewards": -1.4199671201573505,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010156425638997,
    "equal_rewards": -2.0021179916962932,
    "random_rewards": -1.7707235612429606,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.008612361740431,
    "equal_rewards": -1.9896099467473962,
    "random_rewards": -2.180315154648264,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0201653939675244,
    "equal_rewards": -2.0448687134457995,
    "random_rewards": -2.3950347001304726,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007282652466797,
    "equal_rewards": -2.054247812928898,
    "random_rewards": -2.2338788052767677,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0144563973091545,
    "equal_rewards": -2.035138269527712,
    "random_rewards": -2.249874157644196,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.02073946532054,
    "equal_rewards": -1.986006645907132,
    "random_rewards": -1.756845823298492,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.988458018183581,
    "equal_rewards": -2.0359225782345156,
    "random_rewards": -2.8307814044573623,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.034343982180755,
    "equal_rewards": -2.013685862562006,
    "random_rewards": -0.8690667565782341,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.960605281796335,
    "equal_rewards": -1.9942637442411066,
    "random_rewards": -1.324575505437209,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9983265818024316,
    "equal_rewards": -1.9817370078197323,
    "random_rewards": -1.2840746261755913,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9880681320419724,
    "equal_rewards": -2.009313461928492,
    "random_rewards": -2.233157380750227,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0344766216158012,
    "equal_rewards": -2.016579213359414,
    "random_rewards": -1.7976107752836818,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.008660983815589,
    "equal_rewards": -2.0411184659119956,
    "random_rewards": -1.5081782072991918,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0013968440811984,
    "equal_rewards": -2.0524696211876114,
    "random_rewards": -2.396346121089664,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0057331036672252,
    "equal_rewards": -2.0479740642565236,
    "random_rewards": -2.539078560332963,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021345908038814,
    "equal_rewards": -2.002513597249484,
    "random_rewards": -1.930592760413342,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0281910837091814,
    "equal_rewards": -2.027104489597739,
    "random_rewards": -2.1127455520221776,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0160079257619565,
    "equal_rewards": -2.0073112715290033,
    "random_rewards": -1.3648263701994048,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9686342124297749,
    "equal_rewards": -2.019669772723261,
    "random_rewards": -1.1435395155657382,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0368821184636214,
    "equal_rewards": -2.024288064681374,
    "random_rewards": -1.0435462953831685,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0536937410284324,
    "equal_rewards": -2.023431661763135,
    "random_rewards": -2.061462304281219,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9992067944968128,
    "equal_rewards": -2.009499927154062,
    "random_rewards": -1.7635883220799982,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.967612983399532,
    "equal_rewards": -2.016655481220479,
    "random_rewards": -2.199136567847943,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9983451667954457,
    "equal_rewards": -2.019441124781939,
    "random_rewards": -0.7486933560470986,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007757445975848,
    "equal_rewards": -2.019401836534669,
    "random_rewards": -1.1484194350864196,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0166982785016536,
    "equal_rewards": -2.035328922532386,
    "random_rewards": -2.535334224958154,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0445204503728194,
    "equal_rewards": -2.02908324253998,
    "random_rewards": -1.1984437122929408,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9786905714463348,
    "equal_rewards": -1.99626460960335,
    "random_rewards": -1.7961999233782242,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.99024697224815,
    "equal_rewards": -1.9714774549978398,
    "random_rewards": -1.1449526261852723,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9878851570655014,
    "equal_rewards": -1.9965677259182555,
    "random_rewards": -1.6064967675975885,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9909759678297658,
    "equal_rewards": -2.0418328775182664,
    "random_rewards": -1.04932378522195,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.014717225773537,
    "equal_rewards": -2.001804687447235,
    "random_rewards": -2.2165813942997548,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9876746466786313,
    "equal_rewards": -2.033347548176704,
    "random_rewards": -2.053343215328372,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9789317999762985,
    "equal_rewards": -2.0325504419428393,
    "random_rewards": -0.9142352983841076,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9767998919543843,
    "equal_rewards": -2.014315009236317,
    "random_rewards": -1.6514829578279837,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9857841257787068,
    "equal_rewards": -2.006460661473218,
    "random_rewards": -1.9242943191438684,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.984863212190997,
    "equal_rewards": -1.9949891600541867,
    "random_rewards": -2.3083067462043596,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9794036535778927,
    "equal_rewards": -2.024300771397211,
    "random_rewards": -1.0441458352846926,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000826224549476,
    "equal_rewards": -2.020599354372712,
    "random_rewards": -1.9435367896287012,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9893648588446395,
    "equal_rewards": -2.0105181670671683,
    "random_rewards": -1.5911425866882007,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0546597935920152,
    "equal_rewards": -2.028211752775015,
    "random_rewards": -1.6086562043765702,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0274564481947017,
    "equal_rewards": -2.0208242466288695,
    "random_rewards": -1.6406465313015959,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0457774355631306,
    "equal_rewards": -2.0205268615766108,
    "random_rewards": -1.9396767263798842,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9963428244763823,
    "equal_rewards": -2.0065103412208343,
    "random_rewards": -0.5875264583733394,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.997782450173844,
    "equal_rewards": -2.030657752448727,
    "random_rewards": -1.463882129097855,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010780991169956,
    "equal_rewards": -2.0277547605721633,
    "random_rewards": -2.525379587087473,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.039949353139905,
    "equal_rewards": -2.01648269953499,
    "random_rewards": -1.6285017654374805,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.996306833589791,
    "equal_rewards": -2.046867336960317,
    "random_rewards": -1.3194028698529974,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.031936429035594,
    "equal_rewards": -1.996734365882488,
    "random_rewards": -0.7298667891396989,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.995633700282499,
    "equal_rewards": -1.9994534426651596,
    "random_rewards": -2.3418623570592443,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9808522654759186,
    "equal_rewards": -1.9910847206966849,
    "random_rewards": -1.879515095914721,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9859144364191268,
    "equal_rewards": -2.018784504927657,
    "random_rewards": -2.037733717022512,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016143361893348,
    "equal_rewards": -2.033119052791604,
    "random_rewards": -2.527505498178093,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9980613238963667,
    "equal_rewards": -1.995017065296596,
    "random_rewards": -1.3189442074242188,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.031763964937097,
    "equal_rewards": -2.0084581229482805,
    "random_rewards": -1.8828374483435848,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9908622379544607,
    "equal_rewards": -2.023781500772373,
    "random_rewards": -3.1097130377721824,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9980590898968598,
    "equal_rewards": -2.0228568486592287,
    "random_rewards": -1.47413219381919,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0331525269930375,
    "equal_rewards": -2.0297855862581877,
    "random_rewards": -1.785123628016764,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013117574688792,
    "equal_rewards": -2.0209470177030546,
    "random_rewards": -1.9152415020423366,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0236881034373364,
    "equal_rewards": -1.9831027259731637,
    "random_rewards": -2.323684068772049,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0047322236092118,
    "equal_rewards": -2.036414426746776,
    "random_rewards": -0.7524687123006544,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.014262213333033,
    "equal_rewards": -1.9984720329225094,
    "random_rewards": -2.4843027727641394,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9974302958047359,
    "equal_rewards": -2.02423848961719,
    "random_rewards": -1.5272057190892314,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9954795540921448,
    "equal_rewards": -2.0258061403234717,
    "random_rewards": -1.317008753506677,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0462812835846247,
    "equal_rewards": -2.0112363890868927,
    "random_rewards": -1.7588088958322423,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.018232890762257,
    "equal_rewards": -2.036101683815572,
    "random_rewards": -1.9058855926266696,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0155050338997844,
    "equal_rewards": -2.0105107919039376,
    "random_rewards": -1.3388005868604804,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0022349297586173,
    "equal_rewards": -2.0517740672369467,
    "random_rewards": -0.5929706518527826,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0130836779892523,
    "equal_rewards": -2.02103066149557,
    "random_rewards": -2.17303190199886,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0232408103882387,
    "equal_rewards": -1.9860939491852703,
    "random_rewards": -2.0146652489019834,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9998557663428507,
    "equal_rewards": -2.0372700821765957,
    "random_rewards": -1.9583231169116075,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9925661091136595,
    "equal_rewards": -2.0094754724526815,
    "random_rewards": -1.4638991194911664,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0064529869394727,
    "equal_rewards": -2.0412540748630135,
    "random_rewards": -0.8958986851894107,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0604657660582357,
    "equal_rewards": -2.018707885113015,
    "random_rewards": -1.7888130983201451,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0331372946169664,
    "equal_rewards": -2.0278053907013924,
    "random_rewards": -1.3565979562236647,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0246059039805178,
    "equal_rewards": -1.9995489667435031,
    "random_rewards": -1.3296751534505837,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9848594620869267,
    "equal_rewards": -2.0325186868827534,
    "random_rewards": -1.6137571463843878,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0081736224828255,
    "equal_rewards": -2.050327516935235,
    "random_rewards": -2.387072670319521,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0531488953323587,
    "equal_rewards": -2.018711649949073,
    "random_rewards": -1.7801450791778428,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.01087476190948,
    "equal_rewards": -2.026850574549667,
    "random_rewards": -1.9132106150152683,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0126739805867278,
    "equal_rewards": -2.004920926537111,
    "random_rewards": -1.3174686303259286,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9908584940401834,
    "equal_rewards": -2.0519145314358584,
    "random_rewards": -2.407007480804913,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.009225628379568,
    "equal_rewards": -2.0449860467053598,
    "random_rewards": -1.795597504424218,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0302994375139356,
    "equal_rewards": -1.9971747509702897,
    "random_rewards": -1.4919747273243074,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9910256252692276,
    "equal_rewards": -2.015767881636651,
    "random_rewards": -2.089419189329884,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013470150075314,
    "equal_rewards": -1.9823829978018708,
    "random_rewards": -2.9015883174236707,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0203112541747394,
    "equal_rewards": -2.0387222237633873,
    "random_rewards": -2.191920654414833,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0046970340778727,
    "equal_rewards": -2.0470787003933095,
    "random_rewards": -1.9488337143030923,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.001772898830678,
    "equal_rewards": -2.028140352926994,
    "random_rewards": -2.0888254548962366,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0218530602055362,
    "equal_rewards": -2.0052539155210396,
    "random_rewards": -2.2315773172544855,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9912389061903397,
    "equal_rewards": -2.022095294598259,
    "random_rewards": -2.235372385003126,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0133758943727664,
    "equal_rewards": -1.997550691039271,
    "random_rewards": -1.458136854629858,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9919155621536424,
    "equal_rewards": -2.0305882581890957,
    "random_rewards": -1.192249420989103,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.057643878183734,
    "equal_rewards": -2.0205415885559335,
    "random_rewards": -0.7370568831029197,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0488237833071534,
    "equal_rewards": -2.0282268635784497,
    "random_rewards": -1.044408073423599,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.01648727284179,
    "equal_rewards": -2.027587019509367,
    "random_rewards": -2.5005977693595582,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9948488133030446,
    "equal_rewards": -2.048267526144598,
    "random_rewards": -1.041363677895676,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.04990071168624,
    "equal_rewards": -2.0244903436814803,
    "random_rewards": -1.9134170626736702,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.012541733891997,
    "equal_rewards": -2.0447269742976544,
    "random_rewards": -2.5432042192445747,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0037458453979857,
    "equal_rewards": -2.044185392132267,
    "random_rewards": -2.2590283048438278,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0095012610203113,
    "equal_rewards": -2.034454621610177,
    "random_rewards": -1.7470098633923707,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.01259383137333,
    "equal_rewards": -2.0017223902072048,
    "random_rewards": -1.8687669556497943,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0293762804954945,
    "equal_rewards": -2.0103732265954175,
    "random_rewards": -1.4891446770905195,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0568964245239694,
    "equal_rewards": -2.0181551368095194,
    "random_rewards": -1.315186916547401,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.003623359109793,
    "equal_rewards": -2.0649957732912587,
    "random_rewards": -1.9376831724564716,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9843957855897665,
    "equal_rewards": -2.029767052123713,
    "random_rewards": -0.8973463091272621,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9929029619477658,
    "equal_rewards": -1.98612755439104,
    "random_rewards": -0.992056546775636,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.008568061540504,
    "equal_rewards": -1.9870209039517632,
    "random_rewards": -1.7252932322736503,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9942273809905755,
    "equal_rewards": -2.0382148740662083,
    "random_rewards": -0.9108308708959141,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.019093221546462,
    "equal_rewards": -2.002082501654713,
    "random_rewards": -2.789416256968475,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9976984457401377,
    "equal_rewards": -1.9890207415628083,
    "random_rewards": -1.627004303532544,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.986526675743296,
    "equal_rewards": -2.054691132638832,
    "random_rewards": -1.7877453403234838,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0300803127677627,
    "equal_rewards": -2.010870226977881,
    "random_rewards": -1.5793186567603703,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9948509088241289,
    "equal_rewards": -1.9725001009511094,
    "random_rewards": -1.3312335128924024,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010097188757511,
    "equal_rewards": -1.9665176658361307,
    "random_rewards": -2.1516286186845606,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9766776901944039,
    "equal_rewards": -2.000132890033412,
    "random_rewards": -1.9008055150304615,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9592149443227305,
    "equal_rewards": -2.0103951478028086,
    "random_rewards": -1.6349147533596657,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9734019824156013,
    "equal_rewards": -2.0034567111561654,
    "random_rewards": -2.4934057211734073,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0159185927282586,
    "equal_rewards": -1.9977252054493446,
    "random_rewards": -2.197321323187821,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0344113882160295,
    "equal_rewards": -2.018282726229054,
    "random_rewards": -2.069761452592614,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0148724404349423,
    "equal_rewards": -2.0452802396435548,
    "random_rewards": -2.3962374364576786,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.002157273783008,
    "equal_rewards": -1.9842794980496818,
    "random_rewards": -1.4875881683687084,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9569216012297295,
    "equal_rewards": -1.983503261611927,
    "random_rewards": -1.5730723325846228,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9745616373819328,
    "equal_rewards": -2.023175989619076,
    "random_rewards": -1.1920157230749124,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0060855136227422,
    "equal_rewards": -2.0049620153013312,
    "random_rewards": -1.5898347070490582,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.035805969254383,
    "equal_rewards": -1.9919346210997517,
    "random_rewards": -2.345712145861163,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.002637869077981,
    "equal_rewards": -2.0205013745063036,
    "random_rewards": -2.237453691213194,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.995180627624154,
    "equal_rewards": -2.024037592294194,
    "random_rewards": -0.8798245573103957,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0026837049377515,
    "equal_rewards": -1.9980654660835628,
    "random_rewards": -2.511173487437584,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.00471568060872,
    "equal_rewards": -1.993803190915782,
    "random_rewards": -2.4870826299373716,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0332358398947963,
    "equal_rewards": -2.0143478667552746,
    "random_rewards": -1.6299151431931946,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9992746483102097,
    "equal_rewards": -2.0325147875906215,
    "random_rewards": -1.4871067387041803,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0268799380360165,
    "equal_rewards": -2.0264774834320285,
    "random_rewards": -1.3275984757463688,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9547242538798606,
    "equal_rewards": -1.9965682707080536,
    "random_rewards": -1.4785731364910262,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.971635066983914,
    "equal_rewards": -1.956840321726407,
    "random_rewards": -0.7181274471371548,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0158435915881427,
    "equal_rewards": -1.999007431780785,
    "random_rewards": -2.6123406524612838,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9927174545035469,
    "equal_rewards": -2.0356766301412055,
    "random_rewards": -1.2234578849391469,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9859790321110888,
    "equal_rewards": -1.9507339178181073,
    "random_rewards": -2.003914501734624,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9450680046965458,
    "equal_rewards": -1.905362150232866,
    "random_rewards": -1.2627024107953844,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9101121111291763,
    "equal_rewards": -1.9427553080586901,
    "random_rewards": -2.1059820570924614,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.947176730582038,
    "equal_rewards": -1.9675799007925026,
    "random_rewards": -0.8713609512758127,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0043281999645712,
    "equal_rewards": -2.0355867042986286,
    "random_rewards": -2.6894179532412306,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.934980643954741,
    "equal_rewards": -1.9975825974151573,
    "random_rewards": -2.4585484724127045,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004148014414616,
    "equal_rewards": -1.9739753250387375,
    "random_rewards": -1.149984875098064,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9965852572106,
    "equal_rewards": -2.021600042623268,
    "random_rewards": -1.1872416049996093,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8972013648046446,
    "equal_rewards": -1.9399689392109618,
    "random_rewards": -1.6851869405200453,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9075555122978858,
    "equal_rewards": -1.8887493932268864,
    "random_rewards": -2.361033256523423,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8937448762942417,
    "equal_rewards": -1.934302053576487,
    "random_rewards": -1.2748291243761836,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9136916761813736,
    "equal_rewards": -1.9168383723870375,
    "random_rewards": -1.1001405568134044,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9305273992599723,
    "equal_rewards": -1.9240350549734615,
    "random_rewards": -1.8231416527941033,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9301087623382536,
    "equal_rewards": -1.956986965134207,
    "random_rewards": -2.451279595098491,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8890756757862004,
    "equal_rewards": -1.9107788260594183,
    "random_rewards": -2.8048530446893776,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8897350243864723,
    "equal_rewards": -1.877744605248074,
    "random_rewards": -1.5116491026956127,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9427464817073186,
    "equal_rewards": -1.9637812611547245,
    "random_rewards": -1.1510913466533443,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0018052032207034,
    "equal_rewards": -2.011003526531026,
    "random_rewards": -1.4787157503336437,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9567336232247468,
    "equal_rewards": -2.022110414232279,
    "random_rewards": -2.110555618170732,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0332974201347156,
    "equal_rewards": -1.9954853133478427,
    "random_rewards": -1.177402418129798,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8788285972966894,
    "equal_rewards": -1.9312870404934537,
    "random_rewards": -2.2437231701399276,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.930315119176997,
    "equal_rewards": -1.9552000402002703,
    "random_rewards": -2.432841031153745,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0338336044773473,
    "equal_rewards": -1.9862686373179197,
    "random_rewards": -1.7087045208626188,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.957652543535089,
    "equal_rewards": -1.9614624829224447,
    "random_rewards": -1.290182743476107,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9760606775903145,
    "equal_rewards": -1.9930602880497652,
    "random_rewards": -2.4823057195547675,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.006457649796444,
    "equal_rewards": -1.9862825703049363,
    "random_rewards": -2.764720564528785,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9375387477762775,
    "equal_rewards": -1.9162576012430224,
    "random_rewards": -2.086869757118087,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8643451954419357,
    "equal_rewards": -1.9372368118499903,
    "random_rewards": -2.1143462636676293,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.939674986345873,
    "equal_rewards": -1.9487793030533047,
    "random_rewards": -1.2833424678643712,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.945507402090827,
    "equal_rewards": -1.9935257395843622,
    "random_rewards": -2.4562002792932525,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.031090785015406,
    "equal_rewards": -1.9933416687438794,
    "random_rewards": -1.5930513182450725,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.995942951652101,
    "equal_rewards": -2.018980295426469,
    "random_rewards": -1.4606287989300322,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9701296036955633,
    "equal_rewards": -1.9818895860938393,
    "random_rewards": -1.4721482901949978,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0234402475841375,
    "equal_rewards": -1.9801332239440328,
    "random_rewards": -1.9989006194040484,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8935149874424897,
    "equal_rewards": -1.9660568417079234,
    "random_rewards": -2.442111558239163,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9469992808702488,
    "equal_rewards": -1.9512608667758176,
    "random_rewards": -2.4207147620907,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0146402548965536,
    "equal_rewards": -1.9767683243747864,
    "random_rewards": -1.281407327415971,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9658845947271504,
    "equal_rewards": -1.9515481459401935,
    "random_rewards": -1.4577736245980628,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8966322181015993,
    "equal_rewards": -1.9534834568951407,
    "random_rewards": -2.0230384913786796,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9695209674213092,
    "equal_rewards": -1.983929983873875,
    "random_rewards": -2.189722176731732,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9497397439028616,
    "equal_rewards": -1.987654730633606,
    "random_rewards": -1.2613846108149454,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9407579944459417,
    "equal_rewards": -1.9710033389295214,
    "random_rewards": -0.721738227708657,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.963796228871562,
    "equal_rewards": -1.9987565744854707,
    "random_rewards": -2.1647532125518247,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0296310842317578,
    "equal_rewards": -2.001039981839906,
    "random_rewards": -1.0293229667343233,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.995564286817356,
    "equal_rewards": -2.0306132150013982,
    "random_rewards": -2.122303440457025,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0123740815054854,
    "equal_rewards": -1.9723722832516084,
    "random_rewards": -2.158396906651844,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0242344264165197,
    "equal_rewards": -2.0137646725906233,
    "random_rewards": -1.483648559168212,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9955034992987557,
    "equal_rewards": -1.9762420375380092,
    "random_rewards": -1.5860182630950757,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9785467068871898,
    "equal_rewards": -1.9661363267604999,
    "random_rewards": -1.2808492510064315,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9504202082826416,
    "equal_rewards": -1.960233606681001,
    "random_rewards": -2.3134192277463965,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8848554725889268,
    "equal_rewards": -1.9612956520163192,
    "random_rewards": -1.5653950259863976,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9165420829693562,
    "equal_rewards": -1.9662201104168013,
    "random_rewards": -2.4677454215677694,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.951604930601072,
    "equal_rewards": -1.9922797520278048,
    "random_rewards": -2.4709456217000554,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9781363059927424,
    "equal_rewards": -2.0034640671354658,
    "random_rewards": -2.024816885092447,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0321233562308385,
    "equal_rewards": -2.01581353173995,
    "random_rewards": -1.6376245294886034,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9829197327378627,
    "equal_rewards": -2.0338780627202047,
    "random_rewards": -2.554127748896787,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.023037762005039,
    "equal_rewards": -1.9997099950895478,
    "random_rewards": -2.491983105732304,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9839111498842195,
    "equal_rewards": -2.0305013495697892,
    "random_rewards": -2.6717666100279653,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0271198519364733,
    "equal_rewards": -2.0079193396565667,
    "random_rewards": -2.05566720749699,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0266595291797995,
    "equal_rewards": -2.04766440666536,
    "random_rewards": -1.4878264932971348,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9916591394362206,
    "equal_rewards": -2.01354092196551,
    "random_rewards": -1.372873217031762,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.005512932656182,
    "equal_rewards": -1.9855774532174224,
    "random_rewards": -2.171783384383714,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9932356424107214,
    "equal_rewards": -2.020129777682147,
    "random_rewards": -2.2193382677183573,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.962292779126736,
    "equal_rewards": -2.0216808159929833,
    "random_rewards": -2.818268394048059,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.996355890854597,
    "equal_rewards": -2.0246687626058755,
    "random_rewards": -1.6151183608093516,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9859909615941331,
    "equal_rewards": -2.0058767006368017,
    "random_rewards": -2.203218625656644,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9603680263309518,
    "equal_rewards": -1.9820598524305013,
    "random_rewards": -1.013162755905309,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0332754114756297,
    "equal_rewards": -1.9930214081659277,
    "random_rewards": -1.885474134492409,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0179769539626053,
    "equal_rewards": -2.0462129589155302,
    "random_rewards": -1.0381059733556977,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0051334909514864,
    "equal_rewards": -2.0199862796372132,
    "random_rewards": -2.078885973036291,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.033459454365861,
    "equal_rewards": -2.0209304306259566,
    "random_rewards": -2.522420346377158,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0121417978946115,
    "equal_rewards": -2.034966862213097,
    "random_rewards": -1.795694632250718,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007339019085954,
    "equal_rewards": -1.9969820922665211,
    "random_rewards": -1.7858867366859963,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9730977934542717,
    "equal_rewards": -2.0392853678709466,
    "random_rewards": -1.467740787818634,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0421932457312897,
    "equal_rewards": -2.0033292762120443,
    "random_rewards": -1.6240491888452726,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.988497443437243,
    "equal_rewards": -2.023906751700294,
    "random_rewards": -1.606884990762974,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9775042525313555,
    "equal_rewards": -2.0282028969929278,
    "random_rewards": -1.7655801942450513,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0139754351169286,
    "equal_rewards": -2.035134022849907,
    "random_rewards": -2.2209018115941173,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.029001003400528,
    "equal_rewards": -2.01881848305048,
    "random_rewards": -2.066043911511511,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9945513852630476,
    "equal_rewards": -2.0482144472081205,
    "random_rewards": -1.7992379737975028,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.020724390334937,
    "equal_rewards": -1.9870000550056144,
    "random_rewards": -1.7306028563071427,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.983499782991186,
    "equal_rewards": -2.023652106247986,
    "random_rewards": -1.6502916281995121,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.018284926688884,
    "equal_rewards": -2.043790187344996,
    "random_rewards": -2.2216418443908315,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0356266157238645,
    "equal_rewards": -2.004558053324277,
    "random_rewards": -1.7462646971378442,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.01383921800376,
    "equal_rewards": -1.973577323214974,
    "random_rewards": -1.3149922593794918,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9898220108342326,
    "equal_rewards": -2.012301472154281,
    "random_rewards": -2.20139237354706,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.932055279551357,
    "equal_rewards": -1.99561053910733,
    "random_rewards": -1.3628908046454913,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0159672697825255,
    "equal_rewards": -1.9752797134963695,
    "random_rewards": -2.028091774359289,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0054667000137263,
    "equal_rewards": -2.032405843732297,
    "random_rewards": -0.9045549029287733,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9695840221630996,
    "equal_rewards": -2.0076026995967498,
    "random_rewards": -2.3404626751702855,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.990170993295181,
    "equal_rewards": -1.973703507018362,
    "random_rewards": -1.6049751962208365,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010228507711371,
    "equal_rewards": -1.9827442860163762,
    "random_rewards": -2.3401778466475145,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9736528003625957,
    "equal_rewards": -2.0315011140478587,
    "random_rewards": -1.0484142762123962,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.98664621554123,
    "equal_rewards": -1.9986232033232327,
    "random_rewards": -1.325710657547087,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.993677702894851,
    "equal_rewards": -1.9972846661403063,
    "random_rewards": -2.506486883294124,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9555859881107232,
    "equal_rewards": -1.9989296156012628,
    "random_rewards": -1.6180094668220848,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.960631718189044,
    "equal_rewards": -2.0207303764529163,
    "random_rewards": -1.5937203664175252,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9475726626266792,
    "equal_rewards": -2.0099354624450223,
    "random_rewards": -1.1787201258350692,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.957907264521605,
    "equal_rewards": -1.9992240016893894,
    "random_rewards": -1.9019269921050976,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9914337762234924,
    "equal_rewards": -1.9972716109335082,
    "random_rewards": -2.615622239557764,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.02538246245164,
    "equal_rewards": -1.9869247488176636,
    "random_rewards": -1.4456254881373773,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0475335187744763,
    "equal_rewards": -2.0036178154842514,
    "random_rewards": -2.7918446267880035,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9910303596403391,
    "equal_rewards": -2.0356577507355165,
    "random_rewards": -2.0860798870497814,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.02996685400553,
    "equal_rewards": -2.0013988793621023,
    "random_rewards": -1.938650212279439,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011764464784256,
    "equal_rewards": -1.993198420281098,
    "random_rewards": -2.043256266995656,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9508050357713729,
    "equal_rewards": -2.003605070415306,
    "random_rewards": -2.088158947364711,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.005739016543264,
    "equal_rewards": -2.035561258505232,
    "random_rewards": -0.8924470968486699,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.038933638020562,
    "equal_rewards": -1.9934011340397535,
    "random_rewards": -2.0609001854258358,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.965872838670968,
    "equal_rewards": -2.0195303235258764,
    "random_rewards": -1.7900276544988538,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9924808186823282,
    "equal_rewards": -2.0202536993185722,
    "random_rewards": -2.0677300747019087,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0085097354775807,
    "equal_rewards": -2.03476683172252,
    "random_rewards": -2.12364818881005,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0170590763396437,
    "equal_rewards": -2.006557304478152,
    "random_rewards": -2.3265145994006415,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0075335285383917,
    "equal_rewards": -2.0016361863822674,
    "random_rewards": -1.897805521281904,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.018563638487756,
    "equal_rewards": -2.051645685366597,
    "random_rewards": -2.2115830052762204,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0452751397880946,
    "equal_rewards": -2.0023490805158994,
    "random_rewards": -2.041124838316229,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9826402971499717,
    "equal_rewards": -2.014636723971474,
    "random_rewards": -2.6571778244252418,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.00937617335992,
    "equal_rewards": -1.9933215376450113,
    "random_rewards": -1.5893287557516986,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0329056118110738,
    "equal_rewards": -2.008145607872132,
    "random_rewards": -1.4888321632012447,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9822496517618278,
    "equal_rewards": -2.046235757813495,
    "random_rewards": -2.2370372602812756,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0283413432761765,
    "equal_rewards": -2.014837801284218,
    "random_rewards": -2.053326739531392,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.00113799390507,
    "equal_rewards": -2.050181202233677,
    "random_rewards": -1.9267967460108415,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9901207011352202,
    "equal_rewards": -2.0259625093567033,
    "random_rewards": -1.6198607973815138,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9869973011104622,
    "equal_rewards": -2.0154213743834886,
    "random_rewards": -1.7774784028964186,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9798605582673285,
    "equal_rewards": -2.0060487950758477,
    "random_rewards": -1.907311196276079,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0523216998178446,
    "equal_rewards": -2.02265994769737,
    "random_rewards": -2.5299034340785873,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0156564524376672,
    "equal_rewards": -2.0025709999354784,
    "random_rewards": -1.5861244676852828,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9835594930338165,
    "equal_rewards": -2.0030244493028873,
    "random_rewards": -1.187352918578655,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0299440209111097,
    "equal_rewards": -2.0109370932987134,
    "random_rewards": -2.207126078010783,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9883678416261175,
    "equal_rewards": -2.033667303776311,
    "random_rewards": -1.9743978323975324,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9817189446424737,
    "equal_rewards": -2.0069707471996607,
    "random_rewards": -2.063001776141311,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9706794067163234,
    "equal_rewards": -2.0061383489390208,
    "random_rewards": -1.026916789597562,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004278761167948,
    "equal_rewards": -1.974140053260521,
    "random_rewards": -1.4481127706418846,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9882429398983739,
    "equal_rewards": -2.0026041201559934,
    "random_rewards": -1.7804128300669333,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9358988720045938,
    "equal_rewards": -2.0078825529162154,
    "random_rewards": -2.196135576308025,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0252439577644203,
    "equal_rewards": -2.0083346826455335,
    "random_rewards": -1.4825966602484184,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0010546624519874,
    "equal_rewards": -2.0269231832156804,
    "random_rewards": -1.7849307894881792,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004377512354143,
    "equal_rewards": -2.0335419844917166,
    "random_rewards": -2.074662988545792,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9790385525155192,
    "equal_rewards": -1.9913701601164364,
    "random_rewards": -1.2899811474868446,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9577208029613238,
    "equal_rewards": -1.981790682055853,
    "random_rewards": -1.9216304236150195,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0310017145778536,
    "equal_rewards": -1.9904370225297905,
    "random_rewards": -2.3171254983544682,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9983203216975078,
    "equal_rewards": -1.9932428421481503,
    "random_rewards": -2.6217388041585434,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.983460723379911,
    "equal_rewards": -2.0317882662402726,
    "random_rewards": -2.816520900532698,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0105169962615217,
    "equal_rewards": -1.9960209550335377,
    "random_rewards": -1.4297444196800504,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9904416238106666,
    "equal_rewards": -1.978171710853128,
    "random_rewards": -1.7246510780360702,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9650770808097895,
    "equal_rewards": -1.9825489409816908,
    "random_rewards": -1.8832472132898328,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9986789596580024,
    "equal_rewards": -1.983605846616662,
    "random_rewards": -1.5825825288973392,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9216690459367638,
    "equal_rewards": -1.9792356459013187,
    "random_rewards": -1.884563472722914,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.996582742494866,
    "equal_rewards": -1.9953029906128181,
    "random_rewards": -2.764038507565311,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9947380346585393,
    "equal_rewards": -2.0286559820420282,
    "random_rewards": -1.49845075835805,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0037182201638375,
    "equal_rewards": -2.027387430121288,
    "random_rewards": -1.5356507710390366,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021626389522421,
    "equal_rewards": -1.9861479638384183,
    "random_rewards": -1.775635160287057,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9549069388628402,
    "equal_rewards": -2.0218502913234864,
    "random_rewards": -2.7955851245883268,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9973751928501275,
    "equal_rewards": -1.9893741361915664,
    "random_rewards": -1.3400514186627035,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010336622991032,
    "equal_rewards": -1.9781362551184158,
    "random_rewards": -2.3238554743763307,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0158522635169795,
    "equal_rewards": -2.002777067942783,
    "random_rewards": -1.5913954894994835,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9752980849971,
    "equal_rewards": -2.0140072354166914,
    "random_rewards": -1.768396596951241,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9944581978125147,
    "equal_rewards": -2.0501534654840547,
    "random_rewards": -1.522325101963272,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.009166058718247,
    "equal_rewards": -2.0362993169214265,
    "random_rewards": -1.3248600717971324,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0309671435636716,
    "equal_rewards": -2.003594372990551,
    "random_rewards": -1.6322440835724004,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9846473584375155,
    "equal_rewards": -2.0186319367228642,
    "random_rewards": -1.3519826503357348,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9805920226604243,
    "equal_rewards": -1.9997322088399963,
    "random_rewards": -1.0322233560710654,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0073081689015053,
    "equal_rewards": -2.0271402330724055,
    "random_rewards": -2.366487705889207,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0364222573504254,
    "equal_rewards": -2.0224246164525645,
    "random_rewards": -1.9117726869113274,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9506697518242686,
    "equal_rewards": -2.020003814740656,
    "random_rewards": -2.4877435960261676,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.999359784062573,
    "equal_rewards": -1.9904860309650765,
    "random_rewards": -1.4392769418640912,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9744096712373191,
    "equal_rewards": -1.9679472357684364,
    "random_rewards": -1.4345753765882479,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9568173175537797,
    "equal_rewards": -2.0162047259580023,
    "random_rewards": -2.1743001230515504,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0172631883346446,
    "equal_rewards": -2.0082680926940935,
    "random_rewards": -1.759432270914574,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.982477896030498,
    "equal_rewards": -2.0112150246584957,
    "random_rewards": -1.734821656200882,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.944984041426568,
    "equal_rewards": -2.0049523627499815,
    "random_rewards": -2.151110562247249,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9225543684783055,
    "equal_rewards": -1.9727276933647242,
    "random_rewards": -1.338080501061338,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.968962808787213,
    "equal_rewards": -2.0118197058745197,
    "random_rewards": -1.5058124581481607,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.022256556562661,
    "equal_rewards": -1.9920581748052686,
    "random_rewards": -2.019137711668759,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9637177712941547,
    "equal_rewards": -1.9595041591279827,
    "random_rewards": -1.461436654193703,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.026259285543132,
    "equal_rewards": -1.9933763889273823,
    "random_rewards": -0.8572802324614077,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9799296584209312,
    "equal_rewards": -2.027520813350712,
    "random_rewards": -2.056954379159955,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9664480668897206,
    "equal_rewards": -2.011426182589422,
    "random_rewards": -0.5806011100958116,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9813009935931238,
    "equal_rewards": -1.9650155986527653,
    "random_rewards": -1.1800866572320399,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9504420990299363,
    "equal_rewards": -2.0073272444320818,
    "random_rewards": -1.8951495949646326,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.043589525482221,
    "equal_rewards": -2.0072034919821387,
    "random_rewards": -2.5054481353201394,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9830657161554304,
    "equal_rewards": -2.01946140978081,
    "random_rewards": -0.7306695818102147,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0165861271472934,
    "equal_rewards": -1.9798379525835865,
    "random_rewards": -2.617926873840278,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9886132404055572,
    "equal_rewards": -2.052604856013569,
    "random_rewards": -1.0662013535288808,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9909650999263224,
    "equal_rewards": -2.0422899620291437,
    "random_rewards": -1.4970249633919366,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0211383876049274,
    "equal_rewards": -2.0190693251763774,
    "random_rewards": -0.7353671101417587,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.050023813269842,
    "equal_rewards": -2.005419901134134,
    "random_rewards": -1.4360156164198423,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9925873887563024,
    "equal_rewards": -2.035727050442836,
    "random_rewards": -2.681201481071053,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0047357259619414,
    "equal_rewards": -2.0120911810429534,
    "random_rewards": -1.4632622188831532,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9933550754395624,
    "equal_rewards": -2.0195051632163126,
    "random_rewards": -2.3558887800244364,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9977365523867268,
    "equal_rewards": -2.0246064512846513,
    "random_rewards": -1.3143375910245774,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9879168867913097,
    "equal_rewards": -2.0064690861984924,
    "random_rewards": -2.8031193013417686,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.00099716188526,
    "equal_rewards": -2.018001104611411,
    "random_rewards": -2.803253478645795,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0311617461168785,
    "equal_rewards": -1.990283049492592,
    "random_rewards": -1.0113770714597146,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.981460443498333,
    "equal_rewards": -2.0554222237269455,
    "random_rewards": -1.8237606817945216,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0063376014329357,
    "equal_rewards": -2.053830364176746,
    "random_rewards": -1.0681593647748748,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9561492208832314,
    "equal_rewards": -2.0063254215815776,
    "random_rewards": -2.0613245127052995,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9575476124531999,
    "equal_rewards": -1.9408149367323746,
    "random_rewards": -1.5380583406347665,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9370769765119629,
    "equal_rewards": -1.9880605658657293,
    "random_rewards": -1.5861486616853897,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9926641532335045,
    "equal_rewards": -1.9769805935311755,
    "random_rewards": -1.8418323035612998,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.970713056286173,
    "equal_rewards": -1.9819035871271846,
    "random_rewards": -1.8970877720856405,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9674666181763907,
    "equal_rewards": -1.9884997225022558,
    "random_rewards": -1.1334497271100998,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9753251925283055,
    "equal_rewards": -1.9983897730548605,
    "random_rewards": -1.007182936530738,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.036874070014537,
    "equal_rewards": -1.99234444617987,
    "random_rewards": -1.604467760649275,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9806503639523516,
    "equal_rewards": -2.0290262939201535,
    "random_rewards": -0.8923025958348769,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9690531806464016,
    "equal_rewards": -2.0157424476719807,
    "random_rewards": -2.090771211357211,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9804259721886126,
    "equal_rewards": -1.9939680359040688,
    "random_rewards": -1.4294842164963573,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0289622932497737,
    "equal_rewards": -2.0182768587788695,
    "random_rewards": -2.043765628502881,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9687455215572391,
    "equal_rewards": -2.02839400865535,
    "random_rewards": -1.640844478689083,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9985908850485634,
    "equal_rewards": -1.9843171837108498,
    "random_rewards": -1.8613242799089011,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0173725189147973,
    "equal_rewards": -1.9751751018761048,
    "random_rewards": -2.1813974989044715,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9760597267607762,
    "equal_rewards": -2.0177054030372537,
    "random_rewards": -2.0222168816676263,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.992664902881488,
    "equal_rewards": -2.0134391998910104,
    "random_rewards": -0.5972325492474528,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9825920671961539,
    "equal_rewards": -2.0424431393392584,
    "random_rewards": -1.5241573168762206,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9820886248173641,
    "equal_rewards": -2.0195719294326024,
    "random_rewards": -1.2211664364727217,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0061088912904292,
    "equal_rewards": -1.96504559986113,
    "random_rewards": -1.1587485515810612,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9661047032392387,
    "equal_rewards": -2.031072028315278,
    "random_rewards": -1.5169712845435026,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0316599061593563,
    "equal_rewards": -2.00186254874025,
    "random_rewards": -1.6261813265729002,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0055572180098205,
    "equal_rewards": -2.004339465184908,
    "random_rewards": -1.1465369203768359,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9886000892478988,
    "equal_rewards": -2.053220644827773,
    "random_rewards": -1.6816277208315902,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0249252603795944,
    "equal_rewards": -2.001117763549243,
    "random_rewards": -2.0487247533925417,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0234827178859747,
    "equal_rewards": -2.0440886639193176,
    "random_rewards": -1.952118921570928,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0090529847951215,
    "equal_rewards": -2.0349944123144934,
    "random_rewards": -1.2011351055190826,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021655621521731,
    "equal_rewards": -2.0023089141480668,
    "random_rewards": -1.1673997482490113,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0286817065013096,
    "equal_rewards": -2.018131248227229,
    "random_rewards": -1.6211292448701153,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.98928359065344,
    "equal_rewards": -2.0502346067824084,
    "random_rewards": -1.489551576954025,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0363752943074878,
    "equal_rewards": -1.9972425450963125,
    "random_rewards": -2.337079942037777,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9924035007365326,
    "equal_rewards": -2.045274342819275,
    "random_rewards": -2.2217142781444337,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.015854823946079,
    "equal_rewards": -2.0003175309484096,
    "random_rewards": -1.4922757952711638,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9350896479619468,
    "equal_rewards": -1.987766905502771,
    "random_rewards": -1.4912480485291184,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9680676274420954,
    "equal_rewards": -2.010872363113891,
    "random_rewards": -2.0317760649652503,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9766525233081218,
    "equal_rewards": -1.9935564843694817,
    "random_rewards": -2.001748376551435,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9846743912274918,
    "equal_rewards": -2.0111009154225377,
    "random_rewards": -2.650729114699539,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9756016732483954,
    "equal_rewards": -2.0288151408286783,
    "random_rewards": -1.0277982340392193,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0098277434994345,
    "equal_rewards": -2.036243598792659,
    "random_rewards": -1.9555953474564944,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0244089562522123,
    "equal_rewards": -1.9964359502351763,
    "random_rewards": -1.6133067506437362,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9561730942476667,
    "equal_rewards": -2.012686541498253,
    "random_rewards": -1.5107971949785775,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.008726060978802,
    "equal_rewards": -1.9927800725640228,
    "random_rewards": -1.2890791382996158,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013839037494578,
    "equal_rewards": -1.9950506966581556,
    "random_rewards": -2.476988006585165,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0508811359779573,
    "equal_rewards": -2.016954253487076,
    "random_rewards": -1.1526926510475954,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9927017034703578,
    "equal_rewards": -2.011804899106517,
    "random_rewards": -2.202679430212015,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9393467030436877,
    "equal_rewards": -1.9906764971211195,
    "random_rewards": -1.300947358906977,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9074544767993706,
    "equal_rewards": -1.9639124589821273,
    "random_rewards": -2.2824587432591072,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9673489121866115,
    "equal_rewards": -1.9961689621810699,
    "random_rewards": -1.6133083308819671,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9588254727487822,
    "equal_rewards": -1.9796871721431204,
    "random_rewards": -2.142433730480271,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004903399485653,
    "equal_rewards": -1.9640901394047474,
    "random_rewards": -2.1631431741530642,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.975053740828707,
    "equal_rewards": -2.0451214566699703,
    "random_rewards": -1.60924728382934,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0281395717578015,
    "equal_rewards": -2.013954235821497,
    "random_rewards": -2.8007257139644888,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.973635492138679,
    "equal_rewards": -1.995797979388124,
    "random_rewards": -2.605692914224336,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9534689679905421,
    "equal_rewards": -1.9959475992397393,
    "random_rewards": -2.3212467020531413,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.020090077799419,
    "equal_rewards": -1.9955830386264601,
    "random_rewards": -2.067049806762622,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.986543893693981,
    "equal_rewards": -2.0451547559934236,
    "random_rewards": -2.287001185684576,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9932752178972475,
    "equal_rewards": -2.0200693989579785,
    "random_rewards": -2.648480601925366,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9909508810879146,
    "equal_rewards": -2.049333026182743,
    "random_rewards": -1.215229408041925,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0407025326975887,
    "equal_rewards": -2.010088274727966,
    "random_rewards": -2.651021551395754,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.001854116038055,
    "equal_rewards": -2.0101497230187917,
    "random_rewards": -2.0290960597848953,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004430935135729,
    "equal_rewards": -1.9668147737518025,
    "random_rewards": -1.0280926689202523,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9707586039702627,
    "equal_rewards": -2.0282711161791394,
    "random_rewards": -1.8161172780973613,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.006117813015943,
    "equal_rewards": -2.01348922733412,
    "random_rewards": -1.178831047352788,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9831521137122428,
    "equal_rewards": -2.00844735756856,
    "random_rewards": -1.8874846904793283,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.035386021976154,
    "equal_rewards": -2.0542212019079855,
    "random_rewards": -2.3959330909649688,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0094049483461287,
    "equal_rewards": -2.023090528398174,
    "random_rewards": -1.8063257863858317,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9768045264805445,
    "equal_rewards": -2.00711536847923,
    "random_rewards": -1.3292298144313204,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9939708679278523,
    "equal_rewards": -2.032464930755916,
    "random_rewards": -1.7849598835400706,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0227432909355043,
    "equal_rewards": -2.046678183409001,
    "random_rewards": -2.074486146446133,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9865986370861015,
    "equal_rewards": -2.029197949140779,
    "random_rewards": -0.7577084537466168,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0255174616925355,
    "equal_rewards": -1.9998756585998643,
    "random_rewards": -2.047517822667668,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0260264637549117,
    "equal_rewards": -2.052721921063391,
    "random_rewards": -1.4727739480870428,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.009646006160451,
    "equal_rewards": -2.0441622898065366,
    "random_rewards": -2.0751482394519467,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0145630717606076,
    "equal_rewards": -2.041104944915485,
    "random_rewards": -1.5333645811378651,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9870291387048722,
    "equal_rewards": -2.0181788531308693,
    "random_rewards": -1.041187854506498,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016215390719143,
    "equal_rewards": -1.9999130361428668,
    "random_rewards": -1.3201589773394873,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9788929654672756,
    "equal_rewards": -2.047088448485564,
    "random_rewards": -2.418178435232803,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0483809668579687,
    "equal_rewards": -2.0322329771737278,
    "random_rewards": -1.9413901711323003,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.02648478909504,
    "equal_rewards": -2.0471589404021446,
    "random_rewards": -1.3449425723443393,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.012851656388862,
    "equal_rewards": -2.0294408603342258,
    "random_rewards": -1.4919784844315154,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9440122908255595,
    "equal_rewards": -2.0027581277294813,
    "random_rewards": -1.3338326867258012,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.030140533064005,
    "equal_rewards": -1.9995963211148569,
    "random_rewards": -2.495717011611141,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.025473976379819,
    "equal_rewards": -2.0309713138382097,
    "random_rewards": -1.641761257243755,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.97825873346429,
    "equal_rewards": -1.9911756805761862,
    "random_rewards": -1.6321158139169598,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9802160931630106,
    "equal_rewards": -2.004836434789061,
    "random_rewards": -1.753506654815296,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011065702345563,
    "equal_rewards": -2.0328335587639934,
    "random_rewards": -2.810473102893927,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9769677720956862,
    "equal_rewards": -2.0446478714530385,
    "random_rewards": -2.0686393377431584,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.008247605460171,
    "equal_rewards": -2.0251885367521942,
    "random_rewards": -1.761445672592326,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.032067159906848,
    "equal_rewards": -1.993263833084737,
    "random_rewards": -1.7720097491679383,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.985989587002995,
    "equal_rewards": -2.0583933352848796,
    "random_rewards": -1.3655328286348345,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0346430524836365,
    "equal_rewards": -2.0186138352351364,
    "random_rewards": -1.1868409894300056,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0414067634311523,
    "equal_rewards": -2.0152453228245695,
    "random_rewards": -1.777352039811856,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000603477755132,
    "equal_rewards": -2.0224916527316354,
    "random_rewards": -0.8960180763617345,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9831316414978408,
    "equal_rewards": -2.0331284679115162,
    "random_rewards": -2.067641542188086,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9901178539625815,
    "equal_rewards": -2.02588039397529,
    "random_rewards": -1.8926724595890065,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.050553912332993,
    "equal_rewards": -2.020527796713149,
    "random_rewards": -2.3667114430281546,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9750459770233237,
    "equal_rewards": -2.036121548645298,
    "random_rewards": -1.4746145191172397,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0034974832228514,
    "equal_rewards": -2.0144106902514123,
    "random_rewards": -1.754309558470008,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0199447159632546,
    "equal_rewards": -2.046571860112836,
    "random_rewards": -2.058250651798168,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9918831135219897,
    "equal_rewards": -2.007585372266418,
    "random_rewards": -1.4442754052057853,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.94299320408905,
    "equal_rewards": -1.9693739637124867,
    "random_rewards": -1.5539760842530028,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0259560796835507,
    "equal_rewards": -1.9928999268384238,
    "random_rewards": -1.189611742064741,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9626069493800518,
    "equal_rewards": -1.9835021335816427,
    "random_rewards": -1.314906491444699,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.943808978309,
    "equal_rewards": -1.973559394639815,
    "random_rewards": -1.744662226295623,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0441465292331986,
    "equal_rewards": -1.998183629049086,
    "random_rewards": -1.7286485673236824,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9535145400414882,
    "equal_rewards": -2.02075806500872,
    "random_rewards": -2.6762520261447307,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0278876929715697,
    "equal_rewards": -2.0497957385648506,
    "random_rewards": -1.647679714487463,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0276653831440594,
    "equal_rewards": -1.9900417539118114,
    "random_rewards": -0.863095221849469,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.965418316865287,
    "equal_rewards": -2.0081150345978367,
    "random_rewards": -1.4463978721502868,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.989432241087621,
    "equal_rewards": -2.011392345286472,
    "random_rewards": -1.5852596813564908,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.009777886984824,
    "equal_rewards": -2.0352933102045405,
    "random_rewards": -1.4635565080064863,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9692827172284957,
    "equal_rewards": -2.0260056193840006,
    "random_rewards": -1.1802126112788554,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9648784758556355,
    "equal_rewards": -1.9822218293054372,
    "random_rewards": -2.0461492806553676,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.93631346345528,
    "equal_rewards": -1.958161666244981,
    "random_rewards": -1.8471670866146024,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.023816079371616,
    "equal_rewards": -2.00419391386744,
    "random_rewards": -1.7757809189712077,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9730138380828135,
    "equal_rewards": -1.9632495218650776,
    "random_rewards": -1.0126757919931737,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9667257159960871,
    "equal_rewards": -2.02531380221377,
    "random_rewards": -2.0455843380690744,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0493754690796804,
    "equal_rewards": -2.010645066892643,
    "random_rewards": -1.1881923114701063,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9969253907784685,
    "equal_rewards": -2.065605069700938,
    "random_rewards": -2.2234883824290863,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0298574386264807,
    "equal_rewards": -1.9898516228099195,
    "random_rewards": -2.496803140431074,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9396464951318493,
    "equal_rewards": -1.9782428826544596,
    "random_rewards": -2.288437334437205,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9759833149972978,
    "equal_rewards": -2.0341524965850617,
    "random_rewards": -2.4053864016967177,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.035259894130497,
    "equal_rewards": -2.0275317964522945,
    "random_rewards": -2.2208668338040614,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9814542698235047,
    "equal_rewards": -2.04739745421009,
    "random_rewards": -1.7633792477643073,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0375647566633686,
    "equal_rewards": -2.004941382527598,
    "random_rewards": -1.9092566505819812,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0041933626626824,
    "equal_rewards": -1.9957771311126202,
    "random_rewards": -2.5003813503438557,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9785519344627533,
    "equal_rewards": -2.03247092190594,
    "random_rewards": -2.0771580267671874,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9700296602998506,
    "equal_rewards": -1.9872256636940162,
    "random_rewards": -2.0618772554082176,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9732010100524375,
    "equal_rewards": -2.0062827874852203,
    "random_rewards": -2.0463040160482358,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.959906410189103,
    "equal_rewards": -2.011694249418941,
    "random_rewards": -1.0396140273299475,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9998371883137889,
    "equal_rewards": -1.979729769561517,
    "random_rewards": -1.7372320758861624,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9916598662514704,
    "equal_rewards": -1.9815178130279254,
    "random_rewards": -1.4742092682684667,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.999594700132292,
    "equal_rewards": -2.028718434094276,
    "random_rewards": -1.9181239494088629,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010005082350699,
    "equal_rewards": -2.039627816426479,
    "random_rewards": -1.9282678496813004,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.003021230210602,
    "equal_rewards": -2.029608049697677,
    "random_rewards": -1.7367434950667557,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9967603794477684,
    "equal_rewards": -2.0144606591451613,
    "random_rewards": -2.055229230576156,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9874518714370117,
    "equal_rewards": -2.039528027323789,
    "random_rewards": -1.4748423785561635,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9986506109300402,
    "equal_rewards": -2.029748279835237,
    "random_rewards": -1.9473251261944269,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0262368441949485,
    "equal_rewards": -2.0108302576574153,
    "random_rewards": -1.0427269934978363,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0187164136633426,
    "equal_rewards": -2.002976159282589,
    "random_rewards": -2.0295726211153333,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0344019243412372,
    "equal_rewards": -2.0044095986746604,
    "random_rewards": -1.6404419969463409,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0218586170631787,
    "equal_rewards": -2.0109000472539753,
    "random_rewards": -1.1746551455602559,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9502655330065957,
    "equal_rewards": -2.015035663892906,
    "random_rewards": -2.8023559693148035,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9871048254083743,
    "equal_rewards": -2.010062140948399,
    "random_rewards": -1.34026721056848,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.005926356396353,
    "equal_rewards": -2.0088287750407012,
    "random_rewards": -1.3482375704921141,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.970613300546328,
    "equal_rewards": -2.026045169519999,
    "random_rewards": -1.4657500524334792,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9824151694697691,
    "equal_rewards": -2.024183400450717,
    "random_rewards": -1.627519764984648,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013367584247484,
    "equal_rewards": -2.0411153142940766,
    "random_rewards": -1.5321495297129788,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.012338890437402,
    "equal_rewards": -2.0375591323530307,
    "random_rewards": -1.1760423264679711,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.025648346942573,
    "equal_rewards": -2.0179256920165702,
    "random_rewards": -1.7960262899298842,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.044537639059847,
    "equal_rewards": -2.016689980902208,
    "random_rewards": -1.9225840349870407,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.992888156008564,
    "equal_rewards": -2.048451050381077,
    "random_rewards": -1.3890793927278087,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0008716002712443,
    "equal_rewards": -2.019765368079978,
    "random_rewards": -1.6718066843813368,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0076576775946933,
    "equal_rewards": -2.0396922626048126,
    "random_rewards": -0.7532225679234953,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9897945540262127,
    "equal_rewards": -2.050230429976441,
    "random_rewards": -1.6406103706068826,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.026620887515506,
    "equal_rewards": -2.0070000882690753,
    "random_rewards": -0.7277182042603108,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9678419199765549,
    "equal_rewards": -2.0029977886704495,
    "random_rewards": -2.083495898342199,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9786491995317135,
    "equal_rewards": -2.0058423747687364,
    "random_rewards": -1.6064772937236909,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9992565199865653,
    "equal_rewards": -2.0287392457319067,
    "random_rewards": -1.0577709859741524,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.963143101595143,
    "equal_rewards": -2.0137417319421984,
    "random_rewards": -1.4678595016232914,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9637709812445785,
    "equal_rewards": -2.0230622316492566,
    "random_rewards": -1.817065275084903,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0440108465476934,
    "equal_rewards": -1.9967452332232645,
    "random_rewards": -1.7771472799806232,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.024387463439158,
    "equal_rewards": -2.004602862053183,
    "random_rewards": -1.1533010992016148,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9727190068007152,
    "equal_rewards": -2.0195439003660267,
    "random_rewards": -1.3625664966293805,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9642455450478475,
    "equal_rewards": -1.9993135144783172,
    "random_rewards": -1.5854499971721696,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9511530998474118,
    "equal_rewards": -2.0163810239164537,
    "random_rewards": -2.0674410774828385,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0357308463393937,
    "equal_rewards": -1.9930946065215718,
    "random_rewards": -1.8734183637372421,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021810973554465,
    "equal_rewards": -2.0079642813191096,
    "random_rewards": -1.4951909523650475,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0052737796188644,
    "equal_rewards": -2.023581706772203,
    "random_rewards": -1.1979150338834368,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9954610121343597,
    "equal_rewards": -2.039469542169278,
    "random_rewards": -2.523432962821455,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9749396818414862,
    "equal_rewards": -2.033617205926177,
    "random_rewards": -1.0177828768638233,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9974638187910765,
    "equal_rewards": -1.978987895178633,
    "random_rewards": -1.1508796671656985,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9496611294348623,
    "equal_rewards": -2.007982445813746,
    "random_rewards": -1.713897927092996,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0237803914333616,
    "equal_rewards": -1.9899401713070117,
    "random_rewards": -0.8579875854276999,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9325430269266337,
    "equal_rewards": -2.000334345502668,
    "random_rewards": -1.1630160517447472,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9581326844946039,
    "equal_rewards": -1.9685361163478579,
    "random_rewards": -1.165137285431542,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.018735518981661,
    "equal_rewards": -1.9976048655143286,
    "random_rewards": -1.89323727531657,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0185454522499113,
    "equal_rewards": -2.0502769747320144,
    "random_rewards": -1.7605623169289788,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.024582996564403,
    "equal_rewards": -2.0115853559470867,
    "random_rewards": -2.3453150305899055,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9718668000096025,
    "equal_rewards": -2.029936020300591,
    "random_rewards": -1.6347074130083528,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.019379756503916,
    "equal_rewards": -2.033846022328101,
    "random_rewards": -1.5022904043341572,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.036488159920842,
    "equal_rewards": -2.010814840128816,
    "random_rewards": -1.764444764334248,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.980176533523914,
    "equal_rewards": -2.028032514389868,
    "random_rewards": -2.0930039970271888,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.986440724165667,
    "equal_rewards": -2.004127511787739,
    "random_rewards": -1.316726313587431,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0026953253841677,
    "equal_rewards": -1.976775682406216,
    "random_rewards": -2.162374733773894,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9744193696627932,
    "equal_rewards": -2.021342800163896,
    "random_rewards": -0.7464541219544563,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9588793764878047,
    "equal_rewards": -2.016274782133331,
    "random_rewards": -1.9363106723854038,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9753755787613296,
    "equal_rewards": -1.9567462834347542,
    "random_rewards": -1.8478884386757444,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9905044140294255,
    "equal_rewards": -2.008721089667276,
    "random_rewards": -2.359211166647634,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9729378772896684,
    "equal_rewards": -2.0300211611374865,
    "random_rewards": -2.0589303830537338,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.932214309496231,
    "equal_rewards": -1.9132638661556087,
    "random_rewards": -1.84633673128323,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.959561990865501,
    "equal_rewards": -1.948316856405957,
    "random_rewards": -1.6801397160491804,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.990995844174515,
    "equal_rewards": -1.9808276276661223,
    "random_rewards": -1.8708570969791425,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9259157596993572,
    "equal_rewards": -1.9848888557388094,
    "random_rewards": -2.0799276659734853,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.942467751529084,
    "equal_rewards": -2.0045954982923435,
    "random_rewards": -1.3308688890271554,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9669600224074046,
    "equal_rewards": -2.0178026115475314,
    "random_rewards": -2.218862459356826,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9743865394646694,
    "equal_rewards": -2.0165087686218923,
    "random_rewards": -1.4911641172348524,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9686869535552642,
    "equal_rewards": -1.9775710576548218,
    "random_rewards": -2.4350065376978005,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.948008190694728,
    "equal_rewards": -1.9106551021727922,
    "random_rewards": -1.8236005806144462,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9489363295430535,
    "equal_rewards": -1.9731428865799638,
    "random_rewards": -1.5581723893085537,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9735298725854231,
    "equal_rewards": -2.0057946184599387,
    "random_rewards": -0.889667219101083,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9859320413119363,
    "equal_rewards": -2.0232954649212314,
    "random_rewards": -1.6280650994893096,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9861392496213115,
    "equal_rewards": -2.010182485140782,
    "random_rewards": -1.4864169841960266,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0036386256393275,
    "equal_rewards": -1.9954677308945996,
    "random_rewards": -1.8774179774768065,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9750279661750363,
    "equal_rewards": -2.0267029634807954,
    "random_rewards": -1.6641041388603939,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.919224836967222,
    "equal_rewards": -1.94842852818124,
    "random_rewards": -2.4197699450802963,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9361201554947125,
    "equal_rewards": -1.9244971477268549,
    "random_rewards": -0.9782843136649406,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9666014181343816,
    "equal_rewards": -1.986326132954653,
    "random_rewards": -1.621041309180916,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.951276188018494,
    "equal_rewards": -1.9643950201077982,
    "random_rewards": -2.2838484284528207,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.944581338359169,
    "equal_rewards": -1.966504634298186,
    "random_rewards": -1.8949178870846146,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9174784533279228,
    "equal_rewards": -1.946889274077689,
    "random_rewards": -1.2833825654687046,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9718618552544886,
    "equal_rewards": -1.9617742785465748,
    "random_rewards": -0.5777734199336758,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.020829706543988,
    "equal_rewards": -2.0025125735434472,
    "random_rewards": -1.7699996933399937,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9783692786431395,
    "equal_rewards": -2.0395860157392387,
    "random_rewards": -1.2319626457359734,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9784505792434104,
    "equal_rewards": -2.0530452982385743,
    "random_rewards": -2.5622226967848074,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.025866572789131,
    "equal_rewards": -2.013048933572962,
    "random_rewards": -2.0796382347050195,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9455597034645709,
    "equal_rewards": -1.9948177473503679,
    "random_rewards": -1.8807639648371204,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9428802400254788,
    "equal_rewards": -1.9269183304662332,
    "random_rewards": -1.3788048580455379,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9792719219533008,
    "equal_rewards": -1.9577446881489249,
    "random_rewards": -1.4122678762053615,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9714287260398033,
    "equal_rewards": -1.9476429721811241,
    "random_rewards": -1.7243937775707732,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9550035191932225,
    "equal_rewards": -2.007088948394844,
    "random_rewards": -1.0213078066782177,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.025511215421017,
    "equal_rewards": -2.006133148212663,
    "random_rewards": -1.6518095611948136,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9967971510586455,
    "equal_rewards": -2.030857252251441,
    "random_rewards": -1.9081794770061808,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9958768748874056,
    "equal_rewards": -2.0262754682574036,
    "random_rewards": -1.5048473298413179,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.988826805227018,
    "equal_rewards": -1.9668040093778827,
    "random_rewards": -1.4639425111237088,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9853403565143473,
    "equal_rewards": -2.0064510387288546,
    "random_rewards": -2.0406963624461056,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0051925935176316,
    "equal_rewards": -2.029248363551008,
    "random_rewards": -1.1578711921568132,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9445063252806665,
    "equal_rewards": -1.9920021664474419,
    "random_rewards": -1.6192997442556445,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.96333899970245,
    "equal_rewards": -1.995589087716706,
    "random_rewards": -1.1744926557735025,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0040435988482317,
    "equal_rewards": -1.9837888931291583,
    "random_rewards": -1.3126278772305757,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9766924341504217,
    "equal_rewards": -2.004283799222937,
    "random_rewards": -1.6265735986092063,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9423593283580707,
    "equal_rewards": -2.00085394041273,
    "random_rewards": -1.8638702608403077,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9345494618609282,
    "equal_rewards": -1.9966597383461346,
    "random_rewards": -2.152377752601401,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9854771794030426,
    "equal_rewards": -1.9532098615862967,
    "random_rewards": -1.4271246253427852,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9506848707432618,
    "equal_rewards": -1.9904567437492504,
    "random_rewards": -2.1780568820042188,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9616506687037025,
    "equal_rewards": -1.9852174628738402,
    "random_rewards": -1.3102358368427693,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8877513096204406,
    "equal_rewards": -1.947992220401245,
    "random_rewards": -1.7038407236071906,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9255632398944478,
    "equal_rewards": -1.918832710083191,
    "random_rewards": -1.1313284278676685,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9433016881254614,
    "equal_rewards": -1.9164591815569734,
    "random_rewards": -1.1049928322350608,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9670198634106022,
    "equal_rewards": -1.9455448525137924,
    "random_rewards": -1.7342275514159036,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8986190799293539,
    "equal_rewards": -1.9582721401509218,
    "random_rewards": -1.3362004055626775,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8962404813560882,
    "equal_rewards": -1.940086874060007,
    "random_rewards": -1.8016585213163023,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.918483930953725,
    "equal_rewards": -1.9411971719452097,
    "random_rewards": -0.845870179598623,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.922481831137255,
    "equal_rewards": -1.9459811636948552,
    "random_rewards": -1.9929071003106098,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8889452076455322,
    "equal_rewards": -1.8865071084548886,
    "random_rewards": -2.2155736889031847,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8949334116323873,
    "equal_rewards": -1.9544046644128414,
    "random_rewards": -2.715096631642149,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.963017582174078,
    "equal_rewards": -1.9437073654937127,
    "random_rewards": -1.6940854176064701,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.876810225467626,
    "equal_rewards": -1.9387884671703195,
    "random_rewards": -1.991417995046828,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8876232343968504,
    "equal_rewards": -1.9199712173514154,
    "random_rewards": -0.8352562055208693,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9122977550689717,
    "equal_rewards": -1.9021412663803887,
    "random_rewards": -1.545607973325096,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9752282107935344,
    "equal_rewards": -1.9662277610809102,
    "random_rewards": -1.4578420497474087,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9695496417462584,
    "equal_rewards": -2.033590637768345,
    "random_rewards": -2.202366813551751,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9800736418568379,
    "equal_rewards": -2.03692226217217,
    "random_rewards": -2.689626472273739,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.037177434035279,
    "equal_rewards": -2.002091307299473,
    "random_rewards": -2.0802914990935073,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.984516778056575,
    "equal_rewards": -2.036802733541986,
    "random_rewards": -1.683431992637569,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9858365036387897,
    "equal_rewards": -2.0034094688080812,
    "random_rewards": -1.7610770318501898,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9617883185984066,
    "equal_rewards": -2.0127772121803837,
    "random_rewards": -1.0243461086430772,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0341191861229015,
    "equal_rewards": -2.0112028968890865,
    "random_rewards": -2.213693185138549,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0284114229024324,
    "equal_rewards": -2.0073676450259073,
    "random_rewards": -1.019136774130349,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9995684592300809,
    "equal_rewards": -2.0271059426791034,
    "random_rewards": -2.0924774682456966,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.977422227818586,
    "equal_rewards": -2.0070355322178166,
    "random_rewards": -1.7502938329741315,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0230338644053703,
    "equal_rewards": -2.0430606200971573,
    "random_rewards": -0.7312343531962178,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9506824548694985,
    "equal_rewards": -1.984576444213174,
    "random_rewards": -1.909939289969214,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9804760995384405,
    "equal_rewards": -1.9820163691043828,
    "random_rewards": -1.5815861121628123,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9658365578489092,
    "equal_rewards": -2.0336318131699205,
    "random_rewards": -1.5891157540094847,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9940086401927302,
    "equal_rewards": -2.049081788406501,
    "random_rewards": -1.026015897382773,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9401911709348703,
    "equal_rewards": -1.9836634856366002,
    "random_rewards": -1.8799493522335462,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9198483319956088,
    "equal_rewards": -1.977406597758712,
    "random_rewards": -1.8548288901252579,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9532670020962364,
    "equal_rewards": -1.9777001517004202,
    "random_rewards": -2.0423828594441162,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9926115649762577,
    "equal_rewards": -1.970307477457482,
    "random_rewards": -3.027545636093204,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0316000671714662,
    "equal_rewards": -2.0213619238024503,
    "random_rewards": -1.6187116236844354,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.012520864345297,
    "equal_rewards": -2.0380620423143734,
    "random_rewards": -1.9306145682024085,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.012406827747681,
    "equal_rewards": -2.0249482050253267,
    "random_rewards": -2.9702214033233583,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0142172685040665,
    "equal_rewards": -1.9676789388948164,
    "random_rewards": -2.4614294293224033,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.936885582138887,
    "equal_rewards": -1.9995026521567905,
    "random_rewards": -1.737877653547905,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9702711542825868,
    "equal_rewards": -1.989367209613928,
    "random_rewards": -1.352911442283791,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8929533829272487,
    "equal_rewards": -1.9611703361690291,
    "random_rewards": -2.166970734529806,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.003459902083176,
    "equal_rewards": -1.990204108590412,
    "random_rewards": -1.0442366658638873,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9739283959223537,
    "equal_rewards": -2.038603210239131,
    "random_rewards": -1.1766796149683263,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9716378040015854,
    "equal_rewards": -1.9693464533253913,
    "random_rewards": -1.2801832895553131,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9707891690356711,
    "equal_rewards": -2.018604367736713,
    "random_rewards": -1.3523369896301607,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.054819255026201,
    "equal_rewards": -2.005483985485692,
    "random_rewards": -0.8878617220403906,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9770057280606816,
    "equal_rewards": -2.0459282564652876,
    "random_rewards": -1.6414111110730865,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011423267026236,
    "equal_rewards": -1.9863610820331903,
    "random_rewards": -0.8796235000806272,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.972732347667083,
    "equal_rewards": -2.000737767165322,
    "random_rewards": -1.0105217677140184,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.973651714719776,
    "equal_rewards": -1.9637131552768685,
    "random_rewards": -1.710378172847979,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9929858622436891,
    "equal_rewards": -1.979826783111584,
    "random_rewards": -2.3257553223841865,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0239895269546126,
    "equal_rewards": -2.0080598012549915,
    "random_rewards": -2.358499011065904,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.979378111462796,
    "equal_rewards": -2.008571959694445,
    "random_rewards": -1.5798683922729506,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9237705400080036,
    "equal_rewards": -1.9857820081175097,
    "random_rewards": -1.5929884165471768,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9780998279517603,
    "equal_rewards": -2.0053554456001192,
    "random_rewards": -1.5055163247128398,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9513427972895294,
    "equal_rewards": -1.9895526855658745,
    "random_rewards": -1.9248969736908734,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9610844220998818,
    "equal_rewards": -2.0250431466780974,
    "random_rewards": -1.6059374485138882,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0407234541319696,
    "equal_rewards": -1.994471186625634,
    "random_rewards": -1.6089201761816692,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9607697375065851,
    "equal_rewards": -2.034110204023494,
    "random_rewards": -1.3713101991929428,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9902857723496439,
    "equal_rewards": -1.9769917677366298,
    "random_rewards": -2.185499197887822,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9679493489896964,
    "equal_rewards": -2.0318424005878155,
    "random_rewards": -1.7589431392704546,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0011502235428,
    "equal_rewards": -1.9895420839292437,
    "random_rewards": -2.0635798008996096,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.003098562408081,
    "equal_rewards": -2.0347042451327964,
    "random_rewards": -1.9443177284655273,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0112764994722063,
    "equal_rewards": -1.9728262817043987,
    "random_rewards": -1.764680082006426,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.003074387394489,
    "equal_rewards": -2.025975291128174,
    "random_rewards": -1.5080803171502473,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.966979105497725,
    "equal_rewards": -2.0288106318902117,
    "random_rewards": -2.0395654893488113,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.022233933646102,
    "equal_rewards": -2.000505996559341,
    "random_rewards": -1.8995315894729017,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.989320788323979,
    "equal_rewards": -1.971586445363021,
    "random_rewards": -2.592483492761314,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0281993583002755,
    "equal_rewards": -2.0095168292077945,
    "random_rewards": -2.1809300291288225,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9948700742579115,
    "equal_rewards": -2.0513505094449607,
    "random_rewards": -1.7928829721505313,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.019318263582203,
    "equal_rewards": -2.0112890717078673,
    "random_rewards": -1.203086567357078,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9756473025789747,
    "equal_rewards": -2.001874731542663,
    "random_rewards": -2.2345595363583834,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.995608755869175,
    "equal_rewards": -2.042759898833422,
    "random_rewards": -1.9566821869641684,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9868847786991064,
    "equal_rewards": -2.0562313920202353,
    "random_rewards": -0.9085861259993937,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.031070284743872,
    "equal_rewards": -2.0243713210475267,
    "random_rewards": -1.745812943498048,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9889106992645302,
    "equal_rewards": -2.0405115958253415,
    "random_rewards": -1.840075951250003,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0405971114193098,
    "equal_rewards": -2.00187066274991,
    "random_rewards": -1.605536228530225,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9808967135519446,
    "equal_rewards": -2.0467440354172464,
    "random_rewards": -2.0580635882227076,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.028432711604095,
    "equal_rewards": -2.0028845528912305,
    "random_rewards": -2.205136143727026,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.023295140408517,
    "equal_rewards": -2.0186774482998313,
    "random_rewards": -1.945415134890456,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.003560667055099,
    "equal_rewards": -2.0158519103656194,
    "random_rewards": -2.043104386303775,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9686027632059193,
    "equal_rewards": -2.0239142361105666,
    "random_rewards": -2.238874086626242,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9956953831104614,
    "equal_rewards": -2.0220218105093544,
    "random_rewards": -2.4993336737568983,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0047295037246404,
    "equal_rewards": -2.0266046429054616,
    "random_rewards": -0.756490379325056,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9711317393608598,
    "equal_rewards": -2.034227691237722,
    "random_rewards": -1.221732105224255,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0348330694178762,
    "equal_rewards": -1.9960488403234273,
    "random_rewards": -2.6219474254581185,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.969022920312272,
    "equal_rewards": -2.0303288569226603,
    "random_rewards": -1.3292698749422662,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9844093802858829,
    "equal_rewards": -1.9685836004719168,
    "random_rewards": -0.8856053506257093,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0061620202333144,
    "equal_rewards": -1.9881137268728903,
    "random_rewards": -1.741721278901144,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9596259867876862,
    "equal_rewards": -2.0156306482219706,
    "random_rewards": -1.9400475928003011,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9535394329499856,
    "equal_rewards": -2.0132730893285116,
    "random_rewards": -0.874328752444352,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9816419704606136,
    "equal_rewards": -2.0134554958848643,
    "random_rewards": -1.506340353041499,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.989750368895786,
    "equal_rewards": -2.023883004933395,
    "random_rewards": -2.3668481907356864,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.983383693402045,
    "equal_rewards": -2.0050035372491384,
    "random_rewards": -2.0178111211058294,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9859632003307544,
    "equal_rewards": -1.9457717705793367,
    "random_rewards": -0.9997767161909497,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0001731595427223,
    "equal_rewards": -2.0299501414030368,
    "random_rewards": -1.4697791950948256,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9917891746884555,
    "equal_rewards": -2.0202880134568875,
    "random_rewards": -1.1820485831535055,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010285976332126,
    "equal_rewards": -1.9917415731397037,
    "random_rewards": -1.3297768159235805,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9640289737672005,
    "equal_rewards": -2.0246947089062397,
    "random_rewards": -2.0699514862864783,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9639305949733912,
    "equal_rewards": -1.9896789941052795,
    "random_rewards": -1.4480654194721811,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9883460206814094,
    "equal_rewards": -1.96809728135608,
    "random_rewards": -2.0031081690274477,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0061624493572183,
    "equal_rewards": -1.9871544490132256,
    "random_rewards": -1.0298123308045537,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9922622006918387,
    "equal_rewards": -2.0412186355340305,
    "random_rewards": -2.413747974245328,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9609175735974922,
    "equal_rewards": -2.0330684720267094,
    "random_rewards": -1.5001172591948664,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9976602530402094,
    "equal_rewards": -2.0266536267771524,
    "random_rewards": -1.3205146785282786,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9679063814590987,
    "equal_rewards": -2.027052798702708,
    "random_rewards": -2.0623494127992332,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9735461738475768,
    "equal_rewards": -2.0220700782766237,
    "random_rewards": -2.233539388711754,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9977901008440888,
    "equal_rewards": -1.9627466286922077,
    "random_rewards": -2.7240216429896544,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.981157459628656,
    "equal_rewards": -1.9969036783236453,
    "random_rewards": -2.467769632371128,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9682179506874258,
    "equal_rewards": -2.023928130124155,
    "random_rewards": -1.8002038332361028,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.994010694714551,
    "equal_rewards": -2.0310442747668276,
    "random_rewards": -2.20485539241566,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0260032089757964,
    "equal_rewards": -2.006182025717631,
    "random_rewards": -1.930979656447664,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.98166317357772,
    "equal_rewards": -2.0171694727772604,
    "random_rewards": -1.9416232101252136,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.020346594959054,
    "equal_rewards": -1.976070995393244,
    "random_rewards": -1.4540146030295857,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.01450234062617,
    "equal_rewards": -2.0432006346579885,
    "random_rewards": -1.9670129072522882,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0028033949335553,
    "equal_rewards": -1.9826816045242137,
    "random_rewards": -2.152922205794007,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9397997898631312,
    "equal_rewards": -1.9986426386715268,
    "random_rewards": -2.4790266737057993,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9796761309000463,
    "equal_rewards": -2.015536043518622,
    "random_rewards": -2.8024261783398265,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9267097518747223,
    "equal_rewards": -1.9890447468457166,
    "random_rewards": -2.7503938846779397,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9672543467274308,
    "equal_rewards": -1.9920502184404825,
    "random_rewards": -1.5777376543879469,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9934332832045163,
    "equal_rewards": -2.020336905379647,
    "random_rewards": -1.4467653167236532,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0095647724154513,
    "equal_rewards": -2.003040549388299,
    "random_rewards": -1.4711776598585349,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9539779002334519,
    "equal_rewards": -2.024384397714416,
    "random_rewards": -1.9436204246058981,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.997899835138144,
    "equal_rewards": -2.0241500556904706,
    "random_rewards": -1.6285324964238805,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9969332722078181,
    "equal_rewards": -1.986333165863495,
    "random_rewards": -1.6213907773196659,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9843052030644261,
    "equal_rewards": -2.036327075037064,
    "random_rewards": -2.8138536890622263,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.997664338973826,
    "equal_rewards": -2.017353253881649,
    "random_rewards": -2.3577952686047876,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9803293276863672,
    "equal_rewards": -2.013103391607609,
    "random_rewards": -0.889487051587277,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.977339218071871,
    "equal_rewards": -2.0252850098888775,
    "random_rewards": -1.767237098961574,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9896256556537228,
    "equal_rewards": -2.047317207782849,
    "random_rewards": -0.5999575475142517,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0472104290599153,
    "equal_rewards": -2.0287086911765995,
    "random_rewards": -2.5188666171322454,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9912826290411367,
    "equal_rewards": -2.059994378078679,
    "random_rewards": -1.2177327704346677,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0348757159539437,
    "equal_rewards": -1.991324787326155,
    "random_rewards": -2.174590766607476,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.030699816358778,
    "equal_rewards": -1.9885072223076692,
    "random_rewards": -1.4630320332979507,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9792291257244319,
    "equal_rewards": -1.972180310194115,
    "random_rewards": -2.169625875059266,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9671324988981131,
    "equal_rewards": -1.9901155937013362,
    "random_rewards": -1.752610285807834,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.026694095758672,
    "equal_rewards": -2.0100730257597603,
    "random_rewards": -2.1985420368992923,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9825585953292606,
    "equal_rewards": -2.0526110809947826,
    "random_rewards": -2.392152897475398,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0104455200225115,
    "equal_rewards": -1.991081036488202,
    "random_rewards": -2.0570316226430867,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9577374574281192,
    "equal_rewards": -2.010939375881942,
    "random_rewards": -1.3633956437599934,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9962731686713415,
    "equal_rewards": -2.023842965180299,
    "random_rewards": -1.603509782909472,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9854739810136208,
    "equal_rewards": -2.0129886789880516,
    "random_rewards": -1.17960320956297,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9729734060372177,
    "equal_rewards": -2.045758020003648,
    "random_rewards": -2.0529419260462216,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9904380957639063,
    "equal_rewards": -2.049955023022454,
    "random_rewards": -1.9400312751009097,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0190283962194577,
    "equal_rewards": -2.043681210114324,
    "random_rewards": -1.9889322364567117,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.998416304645966,
    "equal_rewards": -2.031813667161398,
    "random_rewards": -1.3578853387690584,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9916644935410175,
    "equal_rewards": -2.0125566179550667,
    "random_rewards": -2.4953288283537667,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.026194211898435,
    "equal_rewards": -2.010158413104365,
    "random_rewards": -1.4716861554424476,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0142485572565856,
    "equal_rewards": -1.9811575126124374,
    "random_rewards": -2.014372726835833,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9764292620688222,
    "equal_rewards": -2.0103527103027883,
    "random_rewards": -1.7651877456317162,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016053072465345,
    "equal_rewards": -2.002546515700793,
    "random_rewards": -0.8844519373767212,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9700184648158063,
    "equal_rewards": -2.0252274894190974,
    "random_rewards": -1.3715592235600835,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9760204588385397,
    "equal_rewards": -2.034881703765513,
    "random_rewards": -0.7533740479976206,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9574321652944078,
    "equal_rewards": -2.0202189537996817,
    "random_rewards": -2.5052636245760076,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9801508373441183,
    "equal_rewards": -2.0160378892832362,
    "random_rewards": -2.043466894377959,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9686492359720482,
    "equal_rewards": -1.956132689978332,
    "random_rewards": -2.028020879554233,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9995689837903965,
    "equal_rewards": -1.9643032572709624,
    "random_rewards": -1.26926096493956,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9549911744926725,
    "equal_rewards": -2.023620467866288,
    "random_rewards": -1.7550421976136517,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.008274092037465,
    "equal_rewards": -2.0347587091212676,
    "random_rewards": -1.6138725739068425,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9875220026060585,
    "equal_rewards": -2.0356217253903983,
    "random_rewards": -1.346029671237819,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0225402072440835,
    "equal_rewards": -2.0068798729991553,
    "random_rewards": -1.3319023845745517,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9810362709766993,
    "equal_rewards": -2.0127182877965244,
    "random_rewards": -2.4953718564166953,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9713128220280158,
    "equal_rewards": -1.9969700214932022,
    "random_rewards": -2.3070475724363337,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0274999654273986,
    "equal_rewards": -2.007952087135982,
    "random_rewards": -1.921688117419076,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0017157406680792,
    "equal_rewards": -2.0224333491306448,
    "random_rewards": -2.0229595406976024,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0123444973845874,
    "equal_rewards": -1.979315042074452,
    "random_rewards": -1.5868205885762496,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9770366799837933,
    "equal_rewards": -2.0338084662711333,
    "random_rewards": -1.6246344394949945,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9861447718604979,
    "equal_rewards": -2.0552363642211984,
    "random_rewards": -1.7953251428079091,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.014244408582509,
    "equal_rewards": -2.01278803227713,
    "random_rewards": -0.8799829349478689,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9841497175801883,
    "equal_rewards": -2.0387797633675073,
    "random_rewards": -1.9210621367638754,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9753149170459272,
    "equal_rewards": -2.005672045894478,
    "random_rewards": -1.4596702906163004,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9721844731645586,
    "equal_rewards": -2.0291705388100336,
    "random_rewards": -2.1072154794103612,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9844821392245677,
    "equal_rewards": -2.022692375457165,
    "random_rewards": -0.8880112867860723,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.989395343064662,
    "equal_rewards": -2.013472193575806,
    "random_rewards": -1.0370846716268036,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9779306564698413,
    "equal_rewards": -2.0457587278876552,
    "random_rewards": -1.935167246738295,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0440756152128263,
    "equal_rewards": -2.0041553842334023,
    "random_rewards": -1.7578795606005795,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0284914852976117,
    "equal_rewards": -2.0126174158084558,
    "random_rewards": -2.2322903406296466,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0554468246113253,
    "equal_rewards": -2.0302250061720795,
    "random_rewards": -2.061872890700986,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9969599765006496,
    "equal_rewards": -2.0529715319049715,
    "random_rewards": -1.3037195409252962,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9850490412698745,
    "equal_rewards": -2.0089594884394217,
    "random_rewards": -1.8145334837086877,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9481244897021541,
    "equal_rewards": -1.9990921648778066,
    "random_rewards": -2.3709879964539144,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9941653428606356,
    "equal_rewards": -2.016731331190738,
    "random_rewards": -1.60934762769132,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9684708384690288,
    "equal_rewards": -2.0260154775929395,
    "random_rewards": -0.7496994737857098,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9982755317156813,
    "equal_rewards": -2.01075010118422,
    "random_rewards": -1.4339807757645362,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9724072113736013,
    "equal_rewards": -2.012226476073484,
    "random_rewards": -1.7564047828872407,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9694887798078562,
    "equal_rewards": -2.027105409993853,
    "random_rewards": -1.0392471273829793,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.98134302366519,
    "equal_rewards": -2.0352582692838888,
    "random_rewards": -2.821469300260419,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9951384689467977,
    "equal_rewards": -2.015898564850001,
    "random_rewards": -0.7401490887917179,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.018530951597633,
    "equal_rewards": -1.997960949200634,
    "random_rewards": -1.352125263503993,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9601691632425602,
    "equal_rewards": -2.014425880585289,
    "random_rewards": -1.789460036568876,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9719853640228984,
    "equal_rewards": -2.0258713647430207,
    "random_rewards": -1.6619173508262943,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9602889919953217,
    "equal_rewards": -1.992790464252959,
    "random_rewards": -1.7132825049266625,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9803314816645328,
    "equal_rewards": -1.9986786867418072,
    "random_rewards": -1.7121430565708002,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9821428981085303,
    "equal_rewards": -2.011010316438207,
    "random_rewards": -0.8700926268213784,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.938502519898777,
    "equal_rewards": -1.994198231846816,
    "random_rewards": -1.4746473324381977,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9836892948331406,
    "equal_rewards": -1.9653194721623035,
    "random_rewards": -2.3006550849558636,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9404127161831135,
    "equal_rewards": -2.0041490992509416,
    "random_rewards": -2.784646864039253,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0349759232141995,
    "equal_rewards": -1.9942251683589025,
    "random_rewards": -1.0096417750871152,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9961784732608412,
    "equal_rewards": -1.9792679834559856,
    "random_rewards": -2.3246151224232925,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9733597695842255,
    "equal_rewards": -2.026933406714378,
    "random_rewards": -1.6258508404198,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0023317984729747,
    "equal_rewards": -2.0311064532730096,
    "random_rewards": -1.3082591595902175,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004679195290285,
    "equal_rewards": -2.0155398094306456,
    "random_rewards": -1.7994764227871087,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9785749850248395,
    "equal_rewards": -2.009377398742055,
    "random_rewards": -1.6250137418038426,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9507904095078468,
    "equal_rewards": -1.9985278435057743,
    "random_rewards": -1.8939247837684334,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.93934935728598,
    "equal_rewards": -1.9978081509311143,
    "random_rewards": -1.4608122321359291,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9498248470728958,
    "equal_rewards": -1.9918607564089361,
    "random_rewards": -1.4575984010738987,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.995077225317829,
    "equal_rewards": -2.0191289950931512,
    "random_rewards": -2.534456774146973,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0460401131783503,
    "equal_rewards": -2.01736465660349,
    "random_rewards": -1.445895885849073,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.972008848305209,
    "equal_rewards": -1.9924676704734023,
    "random_rewards": -1.1769517990778446,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9679518279000672,
    "equal_rewards": -2.022544455058577,
    "random_rewards": -1.4550674138154713,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9731324644944679,
    "equal_rewards": -2.009906174943547,
    "random_rewards": -2.9490992089949586,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9386955404640325,
    "equal_rewards": -1.988980945590448,
    "random_rewards": -1.4776603614577848,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9302188868310788,
    "equal_rewards": -1.9738906879484395,
    "random_rewards": -1.3081424288273398,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9608212781891492,
    "equal_rewards": -1.9960450973634731,
    "random_rewards": -1.020758875170134,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0280523770934833,
    "equal_rewards": -2.0008499860884137,
    "random_rewards": -1.7748289630587286,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9987001444820274,
    "equal_rewards": -2.0474672331200106,
    "random_rewards": -1.0327381403529154,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9818162678971543,
    "equal_rewards": -2.0428133885657496,
    "random_rewards": -1.7983928595982641,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9887753739279694,
    "equal_rewards": -1.975516818216923,
    "random_rewards": -1.6155653877675964,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9811077125870806,
    "equal_rewards": -1.997448958204946,
    "random_rewards": -2.0386328935859854,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0078064531850837,
    "equal_rewards": -2.018655463613528,
    "random_rewards": -1.8975234450132503,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9809323499102107,
    "equal_rewards": -2.0103125762268172,
    "random_rewards": -1.784986127112999,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.970127758708959,
    "equal_rewards": -2.0029612932825374,
    "random_rewards": -2.0247050902446544,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9721645591377424,
    "equal_rewards": -2.0324583072184024,
    "random_rewards": -2.393837722530614,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.030830723177272,
    "equal_rewards": -2.0146177985618965,
    "random_rewards": -1.3506147879836572,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0179864940896475,
    "equal_rewards": -2.0488366011212222,
    "random_rewards": -2.2416093848946645,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0253530827124706,
    "equal_rewards": -2.0467442108904432,
    "random_rewards": -1.2279732302061228,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9780275562380012,
    "equal_rewards": -2.039366105865334,
    "random_rewards": -2.2341781476282767,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9884824570571158,
    "equal_rewards": -1.9834447894095972,
    "random_rewards": -2.0171730416500884,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9346280073907167,
    "equal_rewards": -1.9989686723759785,
    "random_rewards": -0.8672197288035228,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.916479997890721,
    "equal_rewards": -1.9515669136181617,
    "random_rewards": -1.5453107929691725,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9685791645332453,
    "equal_rewards": -2.027405691398672,
    "random_rewards": -1.8035365278358784,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9560237184582958,
    "equal_rewards": -2.0226237739227453,
    "random_rewards": -1.3564015472370379,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.992932268688909,
    "equal_rewards": -2.000899667524205,
    "random_rewards": -1.3289502909165702,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.981470926778428,
    "equal_rewards": -2.015435320151446,
    "random_rewards": -0.9012458229895486,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9877219064865177,
    "equal_rewards": -2.0174587574959384,
    "random_rewards": -2.2142840021296886,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.001983096304875,
    "equal_rewards": -1.9790823849756012,
    "random_rewards": -2.029976842982755,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0154467756470122,
    "equal_rewards": -1.9958031667617946,
    "random_rewards": -2.616548756286976,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9731575753514563,
    "equal_rewards": -2.025701549343405,
    "random_rewards": -2.2113511086643873,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0197592632793286,
    "equal_rewards": -1.9861715069253507,
    "random_rewards": -2.6194469925038226,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.977893044368594,
    "equal_rewards": -2.047960637846317,
    "random_rewards": -2.413865463674982,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.014135300432846,
    "equal_rewards": -2.0371798218348576,
    "random_rewards": -1.7737995544911418,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.04170202742649,
    "equal_rewards": -2.0153374072008834,
    "random_rewards": -2.3881360057111563,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0140049137340506,
    "equal_rewards": -2.039051490646131,
    "random_rewards": -1.6477065775685231,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0306648424724,
    "equal_rewards": -2.0532574799504357,
    "random_rewards": -1.4739960164718318,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0274922265777042,
    "equal_rewards": -2.0187926183371308,
    "random_rewards": -1.9249907950562923,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.998553083938105,
    "equal_rewards": -2.033021855919856,
    "random_rewards": -2.091121799783914,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.977946705322628,
    "equal_rewards": -2.036144469316439,
    "random_rewards": -1.764480555157598,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9593124513559357,
    "equal_rewards": -1.9974410699957756,
    "random_rewards": -1.2759745752338483,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9503368765795883,
    "equal_rewards": -1.9982175236752227,
    "random_rewards": -1.8850905608930348,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9730823577709065,
    "equal_rewards": -2.0234049306766635,
    "random_rewards": -1.192619494305597,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9661127014523956,
    "equal_rewards": -2.002437212925698,
    "random_rewards": -1.7225804311492605,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9683433098034304,
    "equal_rewards": -2.0220453162686556,
    "random_rewards": -1.9294645518741704,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0149710823264453,
    "equal_rewards": -2.0438654288846974,
    "random_rewards": -2.401292110434359,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0035926296861963,
    "equal_rewards": -2.0453822033922666,
    "random_rewards": -1.7693749819883835,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9903706410649296,
    "equal_rewards": -2.05074768890271,
    "random_rewards": -1.946247280213027,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007407352100586,
    "equal_rewards": -2.031200180774193,
    "random_rewards": -0.8770389185300966,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9882937617469187,
    "equal_rewards": -2.0184359246547525,
    "random_rewards": -2.0679284499838735,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9347661527428528,
    "equal_rewards": -1.999773041424619,
    "random_rewards": -1.5686886033068932,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9991622827533821,
    "equal_rewards": -1.9940707913672981,
    "random_rewards": -1.632015166837766,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9873733327815604,
    "equal_rewards": -2.054239438119985,
    "random_rewards": -1.4991813668321345,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0606537612456024,
    "equal_rewards": -2.020334882905725,
    "random_rewards": -1.4880166544029803,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016319311730886,
    "equal_rewards": -2.009326826525155,
    "random_rewards": -2.4836341655376275,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0502590488077175,
    "equal_rewards": -2.0228288689797758,
    "random_rewards": -0.5962856566481016,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0057692912508047,
    "equal_rewards": -2.0305683915716126,
    "random_rewards": -1.0245895193109944,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9702233209973377,
    "equal_rewards": -2.032716314613999,
    "random_rewards": -1.9416342235364645,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.020200889078094,
    "equal_rewards": -1.999336947554149,
    "random_rewards": -1.7135354432403087,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9482137036417513,
    "equal_rewards": -2.004507866674446,
    "random_rewards": -2.477362898957207,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.989833098250724,
    "equal_rewards": -1.9558742388939807,
    "random_rewards": -1.3075515391731565,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9122006898451183,
    "equal_rewards": -1.9679814236483997,
    "random_rewards": -1.1365195558839902,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.975190093950041,
    "equal_rewards": -2.0232220258543228,
    "random_rewards": -1.0462433189083469,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0257136383378933,
    "equal_rewards": -2.006680927367212,
    "random_rewards": -1.9167490888133951,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.049392995129846,
    "equal_rewards": -2.0304372074983954,
    "random_rewards": -1.9037167306709164,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9775970644801344,
    "equal_rewards": -2.0372820946284493,
    "random_rewards": -1.9352888794489438,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9678234683512872,
    "equal_rewards": -1.9994748473423862,
    "random_rewards": -2.176741663473784,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9541587992059397,
    "equal_rewards": -1.983520942245427,
    "random_rewards": -2.7569716001422835,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9428225175478269,
    "equal_rewards": -1.997359555769219,
    "random_rewards": -2.061676348543218,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0245303327470068,
    "equal_rewards": -2.046484171414091,
    "random_rewards": -2.2491499107711768,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.99993392884324,
    "equal_rewards": -2.0498803848560283,
    "random_rewards": -2.425309735731333,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.986931528396841,
    "equal_rewards": -2.031934810032155,
    "random_rewards": -1.1901939929189953,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9645187806365776,
    "equal_rewards": -2.0141104174855697,
    "random_rewards": -1.7819857617059651,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010196222397988,
    "equal_rewards": -1.9973699009386476,
    "random_rewards": -1.3010972936932423,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011017114819615,
    "equal_rewards": -2.039069083545977,
    "random_rewards": -1.8283350076954508,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.995590938427743,
    "equal_rewards": -2.0490657696100656,
    "random_rewards": -2.082130363044273,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9929038381618251,
    "equal_rewards": -2.052182986247592,
    "random_rewards": -2.1235293641581925,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9856527239228687,
    "equal_rewards": -2.038395052847591,
    "random_rewards": -1.1901846954986268,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0022353148254313,
    "equal_rewards": -1.9732975727381898,
    "random_rewards": -1.331130236156786,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9610359128708814,
    "equal_rewards": -2.023644153235635,
    "random_rewards": -1.4858048126559047,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9071374004262243,
    "equal_rewards": -1.9199975226919075,
    "random_rewards": -1.1408549021446188,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8660158522617691,
    "equal_rewards": -1.9255868585446225,
    "random_rewards": -2.2466604511739034,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.002334701792125,
    "equal_rewards": -1.9865025269765686,
    "random_rewards": -1.2900767405874443,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0235137959913057,
    "equal_rewards": -1.996393287887078,
    "random_rewards": -1.4868350972546769,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9883948967807812,
    "equal_rewards": -2.039562612967541,
    "random_rewards": -1.6399757235705978,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.044294201797152,
    "equal_rewards": -2.0265127307056408,
    "random_rewards": -2.9714867066946815,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0163884819729967,
    "equal_rewards": -2.043052093698519,
    "random_rewards": -1.8101687158515638,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0187341570378834,
    "equal_rewards": -2.0064994960128253,
    "random_rewards": -1.4362035860165832,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9406582305602589,
    "equal_rewards": -2.014908659540842,
    "random_rewards": -1.1728075434034804,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0275029433005973,
    "equal_rewards": -2.0006010601244046,
    "random_rewards": -1.1764418834712884,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9873190064637212,
    "equal_rewards": -2.008389362966274,
    "random_rewards": -2.353538835712565,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9233457441768038,
    "equal_rewards": -1.991665974101049,
    "random_rewards": -1.911838290155302,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9627992753542118,
    "equal_rewards": -2.0108662960439285,
    "random_rewards": -2.9426924630769884,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0227568659400497,
    "equal_rewards": -2.043028828029165,
    "random_rewards": -2.204713294937248,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0381132039732393,
    "equal_rewards": -2.02220161006163,
    "random_rewards": -1.6312470787654367,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.969059785648509,
    "equal_rewards": -2.0062721833446897,
    "random_rewards": -2.1836304501508104,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9444617645192046,
    "equal_rewards": -2.003559946727332,
    "random_rewards": -1.3126881303516398,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9214834684420663,
    "equal_rewards": -1.8828680045266473,
    "random_rewards": -0.9648097148283712,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.923056061321395,
    "equal_rewards": -1.9568260887347708,
    "random_rewards": -2.1511673779898186,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9720787412350027,
    "equal_rewards": -2.017869175448894,
    "random_rewards": -1.7710705312960837,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0174523493840657,
    "equal_rewards": -2.0372629523339136,
    "random_rewards": -2.258491268913542,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9852523335246586,
    "equal_rewards": -2.0280647691334406,
    "random_rewards": -2.230230691150586,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9520925458257186,
    "equal_rewards": -2.0240526328110833,
    "random_rewards": -2.3741170115300925,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0310145528416506,
    "equal_rewards": -1.9973522267713268,
    "random_rewards": -1.7737076539151664,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.932218910577644,
    "equal_rewards": -1.9920934661161627,
    "random_rewards": -0.8483436062969826,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.996266952508364,
    "equal_rewards": -1.9797962210978168,
    "random_rewards": -1.158604333523786,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.971022808317234,
    "equal_rewards": -2.0058957185843993,
    "random_rewards": -1.8687484757316992,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9654839859460793,
    "equal_rewards": -2.034189713665476,
    "random_rewards": -1.3365395289894586,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9766009553312527,
    "equal_rewards": -2.029425611755591,
    "random_rewards": -1.929320821286053,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9777338822600834,
    "equal_rewards": -2.013405085918435,
    "random_rewards": -1.6617484116904755,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0375452783668995,
    "equal_rewards": -2.0041605878240567,
    "random_rewards": -2.1951985261697398,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9712528810145746,
    "equal_rewards": -2.0290106595448965,
    "random_rewards": -2.384827574938409,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.987687956851274,
    "equal_rewards": -2.01381706437468,
    "random_rewards": -0.8905693847864389,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9812716099762293,
    "equal_rewards": -2.001937010888124,
    "random_rewards": -1.4412742079240362,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9410785286616647,
    "equal_rewards": -1.9978193978373389,
    "random_rewards": -1.1845136914447638,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9864046958002681,
    "equal_rewards": -2.017153731148449,
    "random_rewards": -2.074324849578601,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0067970228626635,
    "equal_rewards": -1.9949016417896361,
    "random_rewards": -2.482977861848677,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9780422979807444,
    "equal_rewards": -2.033051766584491,
    "random_rewards": -1.332815664266132,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9855214022709071,
    "equal_rewards": -2.0185973868054927,
    "random_rewards": -1.9044642105295257,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9550553033998583,
    "equal_rewards": -1.9708734505273395,
    "random_rewards": -1.323404587260783,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9751359830161763,
    "equal_rewards": -1.9682136454424195,
    "random_rewards": -2.7261038405932307,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9828313082458822,
    "equal_rewards": -2.0294608617501453,
    "random_rewards": -1.8026154660706586,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.029547036671304,
    "equal_rewards": -2.004939965681563,
    "random_rewards": -2.208503838347169,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9937242513532587,
    "equal_rewards": -2.0226440542459536,
    "random_rewards": -1.4971625615083393,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9752873926063823,
    "equal_rewards": -2.0406033745167824,
    "random_rewards": -1.3413576739958617,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.005886534468409,
    "equal_rewards": -1.9895763582338204,
    "random_rewards": -1.9007561253995422,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9624069369506079,
    "equal_rewards": -2.0264558118334404,
    "random_rewards": -1.4897263044228166,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9768285907321252,
    "equal_rewards": -2.0360031558149845,
    "random_rewards": -1.466873049686375,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0111768301702613,
    "equal_rewards": -2.030514459165835,
    "random_rewards": -0.891445372316708,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9872144379412076,
    "equal_rewards": -2.0403982568304233,
    "random_rewards": -2.1196353097037735,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9644047308694508,
    "equal_rewards": -1.990448661517319,
    "random_rewards": -1.602384439761992,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9762074719920668,
    "equal_rewards": -2.0124332643424125,
    "random_rewards": -2.1947630384409917,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9984762743548021,
    "equal_rewards": -1.9828228446321847,
    "random_rewards": -1.7309488782704119,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9802959292009221,
    "equal_rewards": -1.9957550286788193,
    "random_rewards": -1.320887751937038,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.005535638667701,
    "equal_rewards": -1.982279272077391,
    "random_rewards": -1.6148926048216043,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9810657076147904,
    "equal_rewards": -2.041692946343098,
    "random_rewards": -1.3236940865335396,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0094540054467247,
    "equal_rewards": -1.9932851940848288,
    "random_rewards": -1.036174648669725,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9672088289470981,
    "equal_rewards": -2.026866019319767,
    "random_rewards": -1.9111343363308078,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9741704684220385,
    "equal_rewards": -2.0381000024922153,
    "random_rewards": -1.5416215415670504,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9891948425977064,
    "equal_rewards": -2.010208529859646,
    "random_rewards": -2.647591722254168,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0409121934118484,
    "equal_rewards": -2.000349380101307,
    "random_rewards": -2.016585240067363,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0243845655704535,
    "equal_rewards": -2.0314799499384617,
    "random_rewards": -2.2178702891343196,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0136270947384,
    "equal_rewards": -2.0369562550605,
    "random_rewards": -1.8053690876638113,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0043039037810306,
    "equal_rewards": -2.0329876249315255,
    "random_rewards": -2.0895975928227135,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9597580245259918,
    "equal_rewards": -2.0323282463937824,
    "random_rewards": -0.5866288924672207,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.043412707237553,
    "equal_rewards": -2.0052644052946618,
    "random_rewards": -1.334314113796923,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.036340991701929,
    "equal_rewards": -2.022925859167862,
    "random_rewards": -1.4667752410765964,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0048605746720645,
    "equal_rewards": -2.059691929686953,
    "random_rewards": -1.8547739428360153,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0179156748134064,
    "equal_rewards": -2.0451668675300514,
    "random_rewards": -2.859392843325081,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.966199243303938,
    "equal_rewards": -2.0293758165680984,
    "random_rewards": -1.7480950203695023,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9535146132443097,
    "equal_rewards": -2.0175043289669485,
    "random_rewards": -1.6400684766921985,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0065022413246543,
    "equal_rewards": -1.9996579709630475,
    "random_rewards": -2.080557050622492,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9684548198017588,
    "equal_rewards": -2.01232497659028,
    "random_rewards": -2.3834272196518556,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9840305926788777,
    "equal_rewards": -2.040868013696613,
    "random_rewards": -1.9421554961304637,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9861388123210217,
    "equal_rewards": -2.038588862644578,
    "random_rewards": -2.5273593443884064,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9941421617859274,
    "equal_rewards": -2.0572753248996247,
    "random_rewards": -0.9234797322643731,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.022915286534745,
    "equal_rewards": -2.0479686998760505,
    "random_rewards": -1.767650972236491,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.033785746548341,
    "equal_rewards": -2.0229590963406063,
    "random_rewards": -0.8919031946020872,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.057888533119419,
    "equal_rewards": -2.0284605618439855,
    "random_rewards": -1.9401010308045938,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0408040836069397,
    "equal_rewards": -2.0234324847305114,
    "random_rewards": -1.7642546127419856,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9742202435909626,
    "equal_rewards": -2.0018185280827616,
    "random_rewards": -1.9136558495506462,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004905836709285,
    "equal_rewards": -2.0008498971601014,
    "random_rewards": -1.4592552022744054,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0084925772411006,
    "equal_rewards": -2.035248306740577,
    "random_rewards": -2.5343219581423617,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9506474475685243,
    "equal_rewards": -2.0219753066456367,
    "random_rewards": -1.309862446685027,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.987839389416002,
    "equal_rewards": -2.0153487123435245,
    "random_rewards": -2.053581272103242,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0160714306003253,
    "equal_rewards": -2.006296933095907,
    "random_rewards": -1.3137318062780767,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9591281765316244,
    "equal_rewards": -2.003824539927838,
    "random_rewards": -1.5935903164847591,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9480428198186783,
    "equal_rewards": -2.0040973202851795,
    "random_rewards": -1.8666309684699365,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9927833205376666,
    "equal_rewards": -2.024560529620939,
    "random_rewards": -2.3545405515301923,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.984063928934835,
    "equal_rewards": -2.0404339916323,
    "random_rewards": -2.129838314277504,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9931694712772392,
    "equal_rewards": -1.9640428670644787,
    "random_rewards": -1.7309258844841038,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.850252669487678,
    "equal_rewards": -1.8919258383769022,
    "random_rewards": -1.0937611422452909,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9300282150638794,
    "equal_rewards": -1.9734419093255686,
    "random_rewards": -2.3154067373623475,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9628415302173283,
    "equal_rewards": -2.0116819688319314,
    "random_rewards": -1.873678953220956,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9525843353847525,
    "equal_rewards": -1.9905780039702732,
    "random_rewards": -1.5944288232562074,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.933706707551524,
    "equal_rewards": -1.9908873790871568,
    "random_rewards": -0.8823350260183724,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0047161170510908,
    "equal_rewards": -1.9887443855962559,
    "random_rewards": -1.8925237074232628,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9944814546465048,
    "equal_rewards": -2.0210846731428203,
    "random_rewards": -1.3223619149374737,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9647190813684579,
    "equal_rewards": -2.014869713836999,
    "random_rewards": -2.492148490412262,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9731326486949265,
    "equal_rewards": -2.0315201296685155,
    "random_rewards": -1.4920850446137899,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9883538679407358,
    "equal_rewards": -2.022131871347488,
    "random_rewards": -2.344443523976233,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9722684989751391,
    "equal_rewards": -2.0299798336164345,
    "random_rewards": -1.8148839430574752,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9819792271546783,
    "equal_rewards": -2.033293177239555,
    "random_rewards": -1.0278192052680015,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.038609377337477,
    "equal_rewards": -2.0025650150854792,
    "random_rewards": -2.06815172236382,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.991883365100825,
    "equal_rewards": -2.048567984989824,
    "random_rewards": -1.4572379802965911,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021226401306064,
    "equal_rewards": -2.005919035360927,
    "random_rewards": -1.4561108813513288,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9708976874875552,
    "equal_rewards": -2.0010499351723383,
    "random_rewards": -2.5054184966629616,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.985467585540342,
    "equal_rewards": -1.9708624462302902,
    "random_rewards": -1.7415727413822801,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9604709830601357,
    "equal_rewards": -2.024449203523837,
    "random_rewards": -2.0985841521725237,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9975676977864776,
    "equal_rewards": -2.0213230460483116,
    "random_rewards": -1.954235933175233,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.009426499765735,
    "equal_rewards": -2.0372340065083367,
    "random_rewards": -2.840274275210256,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0479778600899583,
    "equal_rewards": -2.018786078717323,
    "random_rewards": -1.4715725656635343,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.003155869272399,
    "equal_rewards": -2.0642103215798695,
    "random_rewards": -1.814690506983252,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0432502575832157,
    "equal_rewards": -2.0290244016940537,
    "random_rewards": -1.6290827921886601,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.033885450281773,
    "equal_rewards": -1.9971715324314032,
    "random_rewards": -1.0018068112619694,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9925213664309815,
    "equal_rewards": -2.0306608144531952,
    "random_rewards": -2.0800698683336174,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9753792048661514,
    "equal_rewards": -2.0520924243172463,
    "random_rewards": -1.4825731383570475,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.001934730662454,
    "equal_rewards": -2.0215331890816324,
    "random_rewards": -1.657065670104584,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9823555906290367,
    "equal_rewards": -2.0086999915266484,
    "random_rewards": -1.3228567691837598,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9535939467381178,
    "equal_rewards": -2.01879578837369,
    "random_rewards": -1.285069410857406,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0245278921128635,
    "equal_rewards": -2.049453222984918,
    "random_rewards": -1.197984122415101,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0245253726562806,
    "equal_rewards": -2.0519107479302208,
    "random_rewards": -1.7747376309169474,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9953226249179823,
    "equal_rewards": -2.0558726711842055,
    "random_rewards": -0.7537859112877945,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.039849923977555,
    "equal_rewards": -2.0220422178552706,
    "random_rewards": -1.602616648850309,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.041004646787647,
    "equal_rewards": -2.0234682477346926,
    "random_rewards": -2.2243499648693508,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.971843147267601,
    "equal_rewards": -2.029030219271267,
    "random_rewards": -0.8990895200313465,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9432213666072633,
    "equal_rewards": -1.9880534202995637,
    "random_rewards": -2.035761571414316,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9567178511764363,
    "equal_rewards": -2.001554002911947,
    "random_rewards": -1.1768161772600971,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9877221211350655,
    "equal_rewards": -2.050163391124558,
    "random_rewards": -2.557805508952695,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.053211389012852,
    "equal_rewards": -2.037473690545616,
    "random_rewards": -1.0343396515392624,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9840508864670372,
    "equal_rewards": -2.0522194992321134,
    "random_rewards": -2.1358273043490663,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9687163455054888,
    "equal_rewards": -1.9995592120730288,
    "random_rewards": -1.5859510958204444,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9924557761596582,
    "equal_rewards": -2.0146994620078,
    "random_rewards": -0.8605384168500563,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9716256903843545,
    "equal_rewards": -2.0263003003502975,
    "random_rewards": -1.800427180980245,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.993338033941143,
    "equal_rewards": -1.972103544741232,
    "random_rewards": -2.4666507230173673,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9599892284364553,
    "equal_rewards": -2.0114269131247924,
    "random_rewards": -0.9987917155118924,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.00842884924273,
    "equal_rewards": -2.057599973384383,
    "random_rewards": -1.9873447596502436,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.044305880756625,
    "equal_rewards": -2.019076602838364,
    "random_rewards": -1.7951929140238614,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.025877534995637,
    "equal_rewards": -1.9939077795533284,
    "random_rewards": -2.3124470571379576,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0033992290160207,
    "equal_rewards": -2.0296222188972517,
    "random_rewards": -1.376826454417799,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0415464735751008,
    "equal_rewards": -2.0051773889477946,
    "random_rewards": -1.7634512164618035,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0183284054267463,
    "equal_rewards": -2.0382100811415387,
    "random_rewards": -2.406022065951611,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.98922343170971,
    "equal_rewards": -2.0455361138817665,
    "random_rewards": -1.8128230559419651,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9616578788989505,
    "equal_rewards": -1.9997828177366666,
    "random_rewards": -1.337607647475629,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9352324416192446,
    "equal_rewards": -1.9958243429317042,
    "random_rewards": -1.711187522416865,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9708729671093566,
    "equal_rewards": -2.037261331722522,
    "random_rewards": -0.9018430509453124,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0240998556544727,
    "equal_rewards": -1.9889571458619617,
    "random_rewards": -1.8827938541323697,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0256531009714394,
    "equal_rewards": -2.010178934499307,
    "random_rewards": -1.451758015237587,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9943003396460743,
    "equal_rewards": -2.059902658698687,
    "random_rewards": -2.2580809658965126,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0225515655345205,
    "equal_rewards": -2.0488950661130825,
    "random_rewards": -1.7815196774595599,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9839400148430029,
    "equal_rewards": -2.0519229920259434,
    "random_rewards": -1.9120133889575632,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.001160258736065,
    "equal_rewards": -2.054850949568167,
    "random_rewards": -0.7362025629748996,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010266492239038,
    "equal_rewards": -2.0411958375709274,
    "random_rewards": -1.4810301488095166,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0157120777909343,
    "equal_rewards": -2.002602891111169,
    "random_rewards": -1.9325062384160214,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9613223950965795,
    "equal_rewards": -2.0262019268951357,
    "random_rewards": -2.355704263194823,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9938158792856375,
    "equal_rewards": -2.0198289954450166,
    "random_rewards": -2.6523500374351743,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.005669098091025,
    "equal_rewards": -1.996154387329039,
    "random_rewards": -2.2011209789366895,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9647326339813673,
    "equal_rewards": -2.024450620735229,
    "random_rewards": -2.0644534501437644,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.005193154571401,
    "equal_rewards": -2.0257568785593523,
    "random_rewards": -1.7873674681297804,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0193331734306335,
    "equal_rewards": -2.0151674657747587,
    "random_rewards": -1.7447330987961152,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9930546112349155,
    "equal_rewards": -2.0239912500485446,
    "random_rewards": -2.25088467452946,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9663007844262723,
    "equal_rewards": -2.0352202758825357,
    "random_rewards": -1.9645420220534022,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0043574166994835,
    "equal_rewards": -2.0312839016933433,
    "random_rewards": -1.4410837767095723,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9814447516814133,
    "equal_rewards": -2.0393102263925647,
    "random_rewards": -1.9171398017920018,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9769654741989633,
    "equal_rewards": -2.0332232232695775,
    "random_rewards": -2.515108317869776,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0170260715875714,
    "equal_rewards": -2.0088194581700014,
    "random_rewards": -1.4590971462736395,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007194012697253,
    "equal_rewards": -1.9762084632663721,
    "random_rewards": -1.148844774136561,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.956032922571021,
    "equal_rewards": -2.0309938503721754,
    "random_rewards": -0.907662424678866,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9939491865507377,
    "equal_rewards": -2.009137983916713,
    "random_rewards": -1.4765896090391786,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9570672189744247,
    "equal_rewards": -2.0138665473607142,
    "random_rewards": -2.0231400200116227,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9862822201103416,
    "equal_rewards": -2.04175858036,
    "random_rewards": -1.6683461507245247,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.993147498215174,
    "equal_rewards": -2.0038476797547555,
    "random_rewards": -2.338436018293301,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0156957187533155,
    "equal_rewards": -1.990899584952409,
    "random_rewards": -1.320118300940224,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.019902685448062,
    "equal_rewards": -2.047666666866105,
    "random_rewards": -2.684482805383336,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9934011097180697,
    "equal_rewards": -2.047028785048159,
    "random_rewards": -2.5622843780077624,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9761496984979625,
    "equal_rewards": -2.002146007356078,
    "random_rewards": -1.8949597583558635,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9669711604675895,
    "equal_rewards": -2.0134182549213935,
    "random_rewards": -2.2545210187957774,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9898113404399707,
    "equal_rewards": -2.0528909841063907,
    "random_rewards": -1.986867683402777,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.019115030735098,
    "equal_rewards": -2.0500454470013154,
    "random_rewards": -1.6650536065176418,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.985832921059694,
    "equal_rewards": -2.0451481487351995,
    "random_rewards": -2.4284429170895914,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0070522381352514,
    "equal_rewards": -1.986504731499356,
    "random_rewards": -1.6329222184618541,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9614335659471147,
    "equal_rewards": -2.0264908615655575,
    "random_rewards": -1.0196183428333154,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.984527963465832,
    "equal_rewards": -1.9995205655052035,
    "random_rewards": -1.6203248281731537,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9922049445791092,
    "equal_rewards": -2.020947188438802,
    "random_rewards": -2.216567725799378,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9573470239886646,
    "equal_rewards": -1.9930808780331375,
    "random_rewards": -1.1505722412051667,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.971169564240292,
    "equal_rewards": -1.9486614869123033,
    "random_rewards": -1.4136423032753398,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9809183880694956,
    "equal_rewards": -2.013781832040599,
    "random_rewards": -1.141353937870723,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9897670655960291,
    "equal_rewards": -2.028797522172065,
    "random_rewards": -2.52776923280242,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.970366048347569,
    "equal_rewards": -2.0269645462646313,
    "random_rewards": -1.9379247013294503,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.990631415651986,
    "equal_rewards": -2.0197661961704645,
    "random_rewards": -1.6571081958593183,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0164249606978233,
    "equal_rewards": -2.003972764389187,
    "random_rewards": -2.3363705207874417,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9948792003103812,
    "equal_rewards": -2.0021080772253805,
    "random_rewards": -1.9261401950136094,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9812084005774877,
    "equal_rewards": -2.04195189876575,
    "random_rewards": -2.0783470497636967,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0214929457474886,
    "equal_rewards": -2.0449040520875927,
    "random_rewards": -1.3550199444241198,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.966907651102882,
    "equal_rewards": -1.9965232600098055,
    "random_rewards": -1.7819607092364547,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0099364480501327,
    "equal_rewards": -2.0370297838259104,
    "random_rewards": -0.7599480113633228,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0232142867922542,
    "equal_rewards": -2.047633277966556,
    "random_rewards": -1.2142496556153395,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9782184798341478,
    "equal_rewards": -2.054178792860323,
    "random_rewards": -1.8152904527006728,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9674377920298913,
    "equal_rewards": -2.02595992806752,
    "random_rewards": -2.5452695614269274,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.987988629255607,
    "equal_rewards": -1.9787331948683458,
    "random_rewards": -1.7255244244526962,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9824612607182512,
    "equal_rewards": -2.0054487239877004,
    "random_rewards": -1.5885562720781423,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9696557041823308,
    "equal_rewards": -2.013134174033471,
    "random_rewards": -1.0282299138642212,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9949114146669022,
    "equal_rewards": -2.0185716721412597,
    "random_rewards": -1.9026263106741514,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0052735657205965,
    "equal_rewards": -2.0217196913007074,
    "random_rewards": -1.3271453932805697,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9900422669197924,
    "equal_rewards": -2.045158253850968,
    "random_rewards": -1.457402219487624,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0100991332799123,
    "equal_rewards": -2.0387916340653085,
    "random_rewards": -1.9564526681912848,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0012642217162457,
    "equal_rewards": -2.053779184863915,
    "random_rewards": -2.1128202492901367,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.002846034171175,
    "equal_rewards": -1.996742198253699,
    "random_rewards": -2.1765352764696844,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9808948101454396,
    "equal_rewards": -2.006025183325167,
    "random_rewards": -1.3210409743848661,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0555026287579103,
    "equal_rewards": -2.024656055833094,
    "random_rewards": -1.3474764999705573,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9666790143977995,
    "equal_rewards": -2.0263962834469162,
    "random_rewards": -1.4738451705262268,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.917389199390282,
    "equal_rewards": -1.9399591596637769,
    "random_rewards": -2.539078539783445,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9201618653077634,
    "equal_rewards": -1.976632630650057,
    "random_rewards": -1.8998301273606297,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.00192586713439,
    "equal_rewards": -2.0605168559926814,
    "random_rewards": -1.6494262786646705,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007218797035092,
    "equal_rewards": -2.031574708124994,
    "random_rewards": -1.7850263602180252,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0282242556086554,
    "equal_rewards": -2.0094658397775147,
    "random_rewards": -2.219405135789108,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9914632901767755,
    "equal_rewards": -2.0554549022560358,
    "random_rewards": -1.9579472386705101,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9982618080825887,
    "equal_rewards": -2.0185081225374484,
    "random_rewards": -1.4582970631911458,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9702561372085003,
    "equal_rewards": -1.9771530868752585,
    "random_rewards": -1.7492077897201224,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9230685014867692,
    "equal_rewards": -1.9726522400146358,
    "random_rewards": -1.8626580330530222,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.98764427527392,
    "equal_rewards": -1.978087160487636,
    "random_rewards": -2.331510791475155,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9988876460504708,
    "equal_rewards": -2.0252643566667565,
    "random_rewards": -2.658683183627402,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9989653056621928,
    "equal_rewards": -2.0268963008443515,
    "random_rewards": -0.601805405435214,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.919780186501507,
    "equal_rewards": -1.9794829905527218,
    "random_rewards": -1.6160755213322384,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9618557086531672,
    "equal_rewards": -1.9939871027297826,
    "random_rewards": -2.771734374492464,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9725111987414226,
    "equal_rewards": -1.9874721199187335,
    "random_rewards": -2.6262249742342587,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9580945671106795,
    "equal_rewards": -2.0227709404877894,
    "random_rewards": -1.4423052548698359,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9887819582354034,
    "equal_rewards": -2.0489859817359766,
    "random_rewards": -1.0435814514217936,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.015600085743963,
    "equal_rewards": -2.001869496419671,
    "random_rewards": -2.3252569683812507,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9583194251147005,
    "equal_rewards": -2.030368590697378,
    "random_rewards": -1.4573836881559763,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.985306078712414,
    "equal_rewards": -2.0271153468919514,
    "random_rewards": -1.9428655235062475,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000624029658042,
    "equal_rewards": -2.0213505134026977,
    "random_rewards": -2.653496134348867,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0243040291582832,
    "equal_rewards": -1.9972054911049568,
    "random_rewards": -2.174664098510175,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9965263155083455,
    "equal_rewards": -2.047017587667733,
    "random_rewards": -2.3970311122085644,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9854422991529588,
    "equal_rewards": -2.016225019299874,
    "random_rewards": -1.4908320353308635,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0262601397309394,
    "equal_rewards": -1.9936784478609473,
    "random_rewards": -1.2920858590397992,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0065667741047584,
    "equal_rewards": -2.0361568072032625,
    "random_rewards": -1.5025742563712186,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.981010635192479,
    "equal_rewards": -2.0412168362602032,
    "random_rewards": -1.9422981990177788,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0051260194573413,
    "equal_rewards": -2.031932289304591,
    "random_rewards": -1.4797637216647814,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9915315211822566,
    "equal_rewards": -2.0202438649917367,
    "random_rewards": -2.1877054388994974,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9975401262337935,
    "equal_rewards": -2.0210639383241937,
    "random_rewards": -2.509338881971691,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9941619076796806,
    "equal_rewards": -2.0573882107445103,
    "random_rewards": -1.3571287537129968,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0334763018359885,
    "equal_rewards": -2.0235477279636296,
    "random_rewards": -2.0575887630467626,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.979017646859407,
    "equal_rewards": -2.038208571111294,
    "random_rewards": -1.2112750900172848,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9815112884606618,
    "equal_rewards": -2.006358707630052,
    "random_rewards": -2.051198010788785,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9932269614433058,
    "equal_rewards": -2.0451135916833882,
    "random_rewards": -2.8294440652675394,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0084462108026297,
    "equal_rewards": -2.019108164907007,
    "random_rewards": -1.4703493993834198,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9801379058443607,
    "equal_rewards": -2.032838393089432,
    "random_rewards": -2.201865427823689,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9921376083731746,
    "equal_rewards": -2.047577544412121,
    "random_rewards": -1.9249106780278122,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.979704476249048,
    "equal_rewards": -2.0270945532367852,
    "random_rewards": -0.7423294160195513,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9914064262677007,
    "equal_rewards": -2.0161968033953377,
    "random_rewards": -2.3383456207438416,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0255599745629893,
    "equal_rewards": -2.050255289862931,
    "random_rewards": -1.621138136578157,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.042199586907099,
    "equal_rewards": -2.0022860118372003,
    "random_rewards": -1.9247879652667925,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9927225391736405,
    "equal_rewards": -2.055620995159314,
    "random_rewards": -1.9802856074115815,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.026989726621783,
    "equal_rewards": -2.013729985304738,
    "random_rewards": -1.5139714947402705,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9736764780683134,
    "equal_rewards": -2.0271397354282024,
    "random_rewards": -1.958129618257225,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.001721890146722,
    "equal_rewards": -2.0293124852542452,
    "random_rewards": -1.7986608490788616,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9890350742195695,
    "equal_rewards": -2.0419399715330875,
    "random_rewards": -0.903196119658659,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9920371518089572,
    "equal_rewards": -2.0605260291885505,
    "random_rewards": -2.2675951831758883,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.964218604147589,
    "equal_rewards": -2.021928423383196,
    "random_rewards": -1.7686728026677665,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9969567899748257,
    "equal_rewards": -1.9860306671764345,
    "random_rewards": -0.7194330648088993,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0226240489714007,
    "equal_rewards": -2.0073632627077833,
    "random_rewards": -2.648359845178655,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0213031461239073,
    "equal_rewards": -2.043206714775465,
    "random_rewards": -1.1881745362017324,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.028261675766763,
    "equal_rewards": -2.022164536620906,
    "random_rewards": -1.331669328994255,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9889945215469473,
    "equal_rewards": -2.0407832716062857,
    "random_rewards": -2.6956785473766534,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9812212345361728,
    "equal_rewards": -2.044371917650595,
    "random_rewards": -1.2125689627251734,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0286390747743517,
    "equal_rewards": -2.0194271775099804,
    "random_rewards": -1.167535549230668,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004672389433223,
    "equal_rewards": -2.0645425896841774,
    "random_rewards": -1.8585246562374853,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0171950353343395,
    "equal_rewards": -2.044785825478482,
    "random_rewards": -1.8066386982820055,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.996295033050979,
    "equal_rewards": -2.020964836669278,
    "random_rewards": -1.588565934400461,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.012874562674427,
    "equal_rewards": -1.997248764968385,
    "random_rewards": -1.482893557303167,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.031767945117119,
    "equal_rewards": -2.0154083486512304,
    "random_rewards": -1.6464793064905345,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.986422684081035,
    "equal_rewards": -2.0407569157850873,
    "random_rewards": -2.1120428653317624,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9943858545093427,
    "equal_rewards": -2.0563425081868933,
    "random_rewards": -1.3307209214775746,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0449268949152373,
    "equal_rewards": -2.0320742252436634,
    "random_rewards": -2.0619739455509802,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9704017260767532,
    "equal_rewards": -2.038424655177546,
    "random_rewards": -2.112119666094882,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.039347590841728,
    "equal_rewards": -1.9987260650819056,
    "random_rewards": -1.327023918495541,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9607367587141322,
    "equal_rewards": -2.017973689985343,
    "random_rewards": -1.3341377741327973,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9960850638319412,
    "equal_rewards": -2.0265836752309925,
    "random_rewards": -2.2514616941524244,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9935780460011865,
    "equal_rewards": -2.0586665393023273,
    "random_rewards": -2.402183389249148,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0001541188278606,
    "equal_rewards": -2.059585094705201,
    "random_rewards": -2.113485981608378,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0321204822962224,
    "equal_rewards": -1.9919298228887983,
    "random_rewards": -0.5816284921290359,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.984201702205803,
    "equal_rewards": -2.0097836642113207,
    "random_rewards": -1.7364844752389321,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000687380254989,
    "equal_rewards": -2.0306205874518195,
    "random_rewards": -1.3316471223396442,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9809615335835247,
    "equal_rewards": -2.0373860461696998,
    "random_rewards": -0.8872660072527794,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9852403203481086,
    "equal_rewards": -2.020094856531447,
    "random_rewards": -1.7946014177500123,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0098984090246534,
    "equal_rewards": -1.9886485028540783,
    "random_rewards": -2.6268928654503716,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9913012108005828,
    "equal_rewards": -2.01349447787566,
    "random_rewards": -1.446763345264574,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9962163772699115,
    "equal_rewards": -2.054443765425778,
    "random_rewards": -1.8324199663244647,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.003742794316576,
    "equal_rewards": -2.033934109752468,
    "random_rewards": -1.2004253382846934,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9758406756966889,
    "equal_rewards": -2.0477063723494346,
    "random_rewards": -2.2161161498238124,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0210935938637054,
    "equal_rewards": -2.0200802795435573,
    "random_rewards": -2.2084601358689637,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9880550766750948,
    "equal_rewards": -2.0416208358939714,
    "random_rewards": -1.9262334498704416,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0117780924419892,
    "equal_rewards": -2.0282132309683396,
    "random_rewards": -2.1067576370908863,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9797565340262138,
    "equal_rewards": -2.0417265611221733,
    "random_rewards": -1.920800513717448,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9824217844370906,
    "equal_rewards": -2.037024894198125,
    "random_rewards": -2.218503758693932,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.964861658508557,
    "equal_rewards": -1.998425135044683,
    "random_rewards": -2.3477757586144876,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9642987494241542,
    "equal_rewards": -1.9880407303090402,
    "random_rewards": -1.7284737035981999,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.992594122921786,
    "equal_rewards": -1.9678410206370196,
    "random_rewards": -2.300993130802795,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9306461384894207,
    "equal_rewards": -1.9996946446750021,
    "random_rewards": -1.646430597654695,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0041629431896935,
    "equal_rewards": -2.0316654163851364,
    "random_rewards": -1.370408072104126,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.986822721848048,
    "equal_rewards": -2.0156929186348367,
    "random_rewards": -1.4739081577536615,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0263267966593803,
    "equal_rewards": -2.001232244693658,
    "random_rewards": -1.5920568335139271,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0353562115687764,
    "equal_rewards": -2.010099215855233,
    "random_rewards": -2.789176406534806,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004465372547436,
    "equal_rewards": -2.06852376368531,
    "random_rewards": -1.5566416438453532,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9869680382580492,
    "equal_rewards": -2.0435535283576645,
    "random_rewards": -1.9687661172519642,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0244914271276184,
    "equal_rewards": -1.9963828492215794,
    "random_rewards": -2.1943103473848464,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.998576140931661,
    "equal_rewards": -2.0308914278960684,
    "random_rewards": -2.1157648613243,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.98025540560408,
    "equal_rewards": -2.042709809523864,
    "random_rewards": -1.4922095644085795,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.01688835361607,
    "equal_rewards": -2.068486366671519,
    "random_rewards": -2.163677367591638,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0137178504377102,
    "equal_rewards": -2.031725575630981,
    "random_rewards": -1.7988345530117846,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0077484788546265,
    "equal_rewards": -2.032183489464731,
    "random_rewards": -1.1885797061234569,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0299144914150156,
    "equal_rewards": -2.0529232551240684,
    "random_rewards": -1.2170391944986976,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.997320480146795,
    "equal_rewards": -2.026948362039499,
    "random_rewards": -1.6005399043707076,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9671754180673962,
    "equal_rewards": -1.9978906450124891,
    "random_rewards": -2.480002619336697,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9813962091467205,
    "equal_rewards": -2.0372245427281857,
    "random_rewards": -1.364706042462962,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9989979936981634,
    "equal_rewards": -2.053934828037946,
    "random_rewards": -2.4031958664096043,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9976470494134848,
    "equal_rewards": -2.0466211245466477,
    "random_rewards": -2.104510908620991,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9732414111418386,
    "equal_rewards": -2.047728964962592,
    "random_rewards": -2.379993448438279,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.023143426394662,
    "equal_rewards": -2.0196339527737353,
    "random_rewards": -2.5112054166573587,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0383335631261996,
    "equal_rewards": -2.0133509464442003,
    "random_rewards": -1.919990660521727,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.99392221338882,
    "equal_rewards": -2.0521578947790022,
    "random_rewards": -1.9149839669332014,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.003337985626027,
    "equal_rewards": -1.9903116577737496,
    "random_rewards": -2.012202024387332,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9980955479820786,
    "equal_rewards": -2.0217737366331696,
    "random_rewards": -2.389038362552314,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9562399984451586,
    "equal_rewards": -2.0181538080615145,
    "random_rewards": -0.7199988784434628,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9632664307539414,
    "equal_rewards": -1.9889907763374133,
    "random_rewards": -2.7648908434850763,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9689977333211826,
    "equal_rewards": -2.0298913413627213,
    "random_rewards": -2.0808316760467322,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.001434490414641,
    "equal_rewards": -2.05459793221287,
    "random_rewards": -2.081146321104998,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000519608818271,
    "equal_rewards": -2.056915645158098,
    "random_rewards": -1.338090971591067,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.029049846944652,
    "equal_rewards": -2.05264773564821,
    "random_rewards": -1.8002799049262463,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0436157873237453,
    "equal_rewards": -2.031176128395445,
    "random_rewards": -1.7662651643574694,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0493611041279003,
    "equal_rewards": -2.03362699121446,
    "random_rewards": -2.2285513001021093,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000779585500181,
    "equal_rewards": -2.062402727751035,
    "random_rewards": -0.5957914835334285,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.014433650943923,
    "equal_rewards": -2.0387431318215263,
    "random_rewards": -2.677076404968992,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9915749430139256,
    "equal_rewards": -2.0477759204319845,
    "random_rewards": -2.518487353101585,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0332170254977577,
    "equal_rewards": -2.0128050913468987,
    "random_rewards": -1.4417117124842123,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.020498153404742,
    "equal_rewards": -2.0464447526545566,
    "random_rewards": -1.3368710755418043,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9899455465958722,
    "equal_rewards": -2.0495308916141344,
    "random_rewards": -1.9280588377427361,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9870053450758816,
    "equal_rewards": -2.0527697290128546,
    "random_rewards": -2.256463676063849,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.984234650813344,
    "equal_rewards": -2.0440763552847487,
    "random_rewards": -1.9491577835671476,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011394954831532,
    "equal_rewards": -1.9985583792186452,
    "random_rewards": -1.1812916660026085,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9811504332631014,
    "equal_rewards": -2.042257223056746,
    "random_rewards": -1.34490109811054,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.994428937549492,
    "equal_rewards": -2.056335459056474,
    "random_rewards": -1.8330339980787294,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0306862375247645,
    "equal_rewards": -2.0525916274457714,
    "random_rewards": -2.2290189256621202,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0504642145942933,
    "equal_rewards": -2.023181273954114,
    "random_rewards": -0.8882259251505867,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0327530108187912,
    "equal_rewards": -2.0171933810072478,
    "random_rewards": -1.3100202703577664,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0049597239253845,
    "equal_rewards": -2.0574295810166774,
    "random_rewards": -1.369649798220348,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0244936526686126,
    "equal_rewards": -2.011238190625075,
    "random_rewards": -1.8799835124802737,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9939799410982908,
    "equal_rewards": -2.0226290302348415,
    "random_rewards": -1.6295547778047041,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9672114945573962,
    "equal_rewards": -2.033858041269914,
    "random_rewards": -2.1092815159284704,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9705191745035617,
    "equal_rewards": -2.031033297365225,
    "random_rewards": -2.373661802138021,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0248677808048097,
    "equal_rewards": -1.995671846698373,
    "random_rewards": -1.0367710523853242,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0077506474021924,
    "equal_rewards": -1.9865082786397212,
    "random_rewards": -1.6092090943806596,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.988294508471688,
    "equal_rewards": -2.048686177754117,
    "random_rewards": -1.9014946282352114,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.020263756509944,
    "equal_rewards": -2.0389952090437538,
    "random_rewards": -0.5958685628032612,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0152580804796507,
    "equal_rewards": -2.0413611296411105,
    "random_rewards": -1.322542812118384,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9830635997184756,
    "equal_rewards": -2.0218666266019123,
    "random_rewards": -1.9507765790901888,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9706336452850164,
    "equal_rewards": -2.0332431957276245,
    "random_rewards": -1.9305206237338117,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9792362673709536,
    "equal_rewards": -2.055172332888257,
    "random_rewards": -2.258372529541276,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0349852988048696,
    "equal_rewards": -2.0142609096997584,
    "random_rewards": -1.3237354001398964,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0340491540487946,
    "equal_rewards": -2.0252613813808398,
    "random_rewards": -2.670904475645262,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0271608167350084,
    "equal_rewards": -2.0520254827193565,
    "random_rewards": -2.2676106075408877,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.98541267633376,
    "equal_rewards": -2.0428990293724802,
    "random_rewards": -2.5424267522005595,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0138459253315655,
    "equal_rewards": -2.036259216108861,
    "random_rewards": -1.6331636142068726,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9936201198207102,
    "equal_rewards": -2.0475656660784596,
    "random_rewards": -1.4665483649183524,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0244498370581034,
    "equal_rewards": -1.9919461193991501,
    "random_rewards": -1.604620442844332,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9637174325187647,
    "equal_rewards": -2.028310390058345,
    "random_rewards": -2.38215303262595,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.982423780326072,
    "equal_rewards": -2.012409570586687,
    "random_rewards": -2.3777237705978345,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9301126027281899,
    "equal_rewards": -2.007782467133377,
    "random_rewards": -1.7512883175633451,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.92998152904374,
    "equal_rewards": -1.98065827448467,
    "random_rewards": -2.768086894205555,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9868145858617994,
    "equal_rewards": -2.0305713262358642,
    "random_rewards": -2.3486218346369134,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.983689925617551,
    "equal_rewards": -2.04245806388415,
    "random_rewards": -1.189613897923596,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0027437808568895,
    "equal_rewards": -1.9851111810943642,
    "random_rewards": -1.4229406144617398,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9610933710930383,
    "equal_rewards": -2.0148621777465436,
    "random_rewards": -1.9306788235885708,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9544690774121272,
    "equal_rewards": -1.9921069685577322,
    "random_rewards": -2.1746735007648006,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9385094420764206,
    "equal_rewards": -1.9982358665319144,
    "random_rewards": -2.646218424410379,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9985674141814638,
    "equal_rewards": -2.0675230690329482,
    "random_rewards": -1.3960569456211815,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.036495806001813,
    "equal_rewards": -2.027293343750867,
    "random_rewards": -1.46557567558805,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9955386427325421,
    "equal_rewards": -2.0507077027820886,
    "random_rewards": -1.5081282575049655,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9946246793498443,
    "equal_rewards": -2.0502118874705193,
    "random_rewards": -1.6296158003389274,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0294309085758107,
    "equal_rewards": -2.0510681225466287,
    "random_rewards": -2.265774460761763,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0522447239681276,
    "equal_rewards": -2.019990119881075,
    "random_rewards": -1.9459222208561695,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0007735162564604,
    "equal_rewards": -2.021851696710857,
    "random_rewards": -1.787991430836326,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9935878152745796,
    "equal_rewards": -2.0495116586398274,
    "random_rewards": -1.0337136348227014,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0388363284477142,
    "equal_rewards": -2.014605046093541,
    "random_rewards": -2.0713122540566036,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.018363562321276,
    "equal_rewards": -2.008288329993911,
    "random_rewards": -0.8664074760064517,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0263808903225486,
    "equal_rewards": -2.0531004548214087,
    "random_rewards": -2.4031934157846053,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004058741987576,
    "equal_rewards": -2.0529234165980754,
    "random_rewards": -0.877881084876355,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0433858108249088,
    "equal_rewards": -2.0274916745272176,
    "random_rewards": -2.065751597984095,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.008195016127197,
    "equal_rewards": -2.0618215425545765,
    "random_rewards": -1.9483783780484984,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0399409822179217,
    "equal_rewards": -2.0130212152101423,
    "random_rewards": -1.760261093846077,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.97479873929684,
    "equal_rewards": -2.035831226445699,
    "random_rewards": -2.379756451076337,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0012692638447156,
    "equal_rewards": -2.0563738786485044,
    "random_rewards": -2.101101763830556,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.01107455851378,
    "equal_rewards": -2.0640668784582132,
    "random_rewards": -1.5242370743078426,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013223750957049,
    "equal_rewards": -2.0639321154038552,
    "random_rewards": -1.034381376995703,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.030561238096259,
    "equal_rewards": -2.017170771317669,
    "random_rewards": -1.486818135747234,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9951447688272252,
    "equal_rewards": -2.0496775781038425,
    "random_rewards": -2.2633415247362256,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.005315029689864,
    "equal_rewards": -1.9925346459527673,
    "random_rewards": -1.8802137458410928,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9724041475748861,
    "equal_rewards": -2.030693547502229,
    "random_rewards": -1.3734221845381065,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9999856660270616,
    "equal_rewards": -2.0571359283502852,
    "random_rewards": -1.7980863829161309,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0188727203796217,
    "equal_rewards": -2.0474147040025663,
    "random_rewards": -1.842623583601805,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004519662926498,
    "equal_rewards": -2.0576298076036603,
    "random_rewards": -1.81165423968292,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0038314931517798,
    "equal_rewards": -2.0550374854968094,
    "random_rewards": -2.5874464375044672,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0041463080195303,
    "equal_rewards": -2.0359857269532986,
    "random_rewards": -1.4831609295573553,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0004446377560896,
    "equal_rewards": -2.035219236245232,
    "random_rewards": -2.6805326526156708,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011549112940438,
    "equal_rewards": -2.044895509069223,
    "random_rewards": -1.6724601369096401,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0380567488976333,
    "equal_rewards": -2.056773150136909,
    "random_rewards": -0.6010812444527588,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0550304041086527,
    "equal_rewards": -2.039078179681439,
    "random_rewards": -1.482814637992273,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.054028420623321,
    "equal_rewards": -2.028266186940719,
    "random_rewards": -2.2360854460662187,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.005328927887844,
    "equal_rewards": -2.0639339481095,
    "random_rewards": -1.363125780500974,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021467137956854,
    "equal_rewards": -2.048595169194693,
    "random_rewards": -1.7977062803482982,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9982652225013642,
    "equal_rewards": -2.054336642649292,
    "random_rewards": -2.2630895938582283,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0075117573703016,
    "equal_rewards": -2.056414027656236,
    "random_rewards": -1.5121881560161126,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0335567826760657,
    "equal_rewards": -2.024312139608202,
    "random_rewards": -1.6388773925849356,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.032487129944336,
    "equal_rewards": -2.0539122380419648,
    "random_rewards": -1.8325065268236482,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.022342529881515,
    "equal_rewards": -2.049030670795407,
    "random_rewards": -2.8634762038227604,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.01136233635397,
    "equal_rewards": -2.049394268277599,
    "random_rewards": -1.4808225483609538,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.046012922009812,
    "equal_rewards": -2.033682158204147,
    "random_rewards": -1.7752680569499284,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9962192241224663,
    "equal_rewards": -2.0497341725643015,
    "random_rewards": -2.835028374396419,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.014873251807768,
    "equal_rewards": -2.0397851265376783,
    "random_rewards": -2.3849586587763394,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0265239256383345,
    "equal_rewards": -2.0533687336586546,
    "random_rewards": -1.38242855312219,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9979235916187212,
    "equal_rewards": -2.0588360774796044,
    "random_rewards": -1.9692458263609454,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0258982325680126,
    "equal_rewards": -2.052603614829936,
    "random_rewards": -1.2157046942116243,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0109463527837788,
    "equal_rewards": -2.0700026862230985,
    "random_rewards": -2.0998101612300992,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010654651079907,
    "equal_rewards": -2.0666661158405932,
    "random_rewards": -1.1932526697950316,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.036833480714814,
    "equal_rewards": -2.0203066680233377,
    "random_rewards": -1.9125248763771237,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.991033384236521,
    "equal_rewards": -2.0203240480088933,
    "random_rewards": -1.6327726975744254,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.003745583302946,
    "equal_rewards": -2.058424831309222,
    "random_rewards": -2.2529490288301273,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.02301773864882,
    "equal_rewards": -2.0509376292134096,
    "random_rewards": -1.9877427745948277,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0041330340046097,
    "equal_rewards": -2.0572954535151,
    "random_rewards": -2.1219752789932933,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010509493970819,
    "equal_rewards": -2.0283469036719417,
    "random_rewards": -1.809616816230941,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9437514457228837,
    "equal_rewards": -2.0181731444731765,
    "random_rewards": -2.797346977935622,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9875651706012818,
    "equal_rewards": -2.040471253281284,
    "random_rewards": -2.2169687221384953,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0025083989511914,
    "equal_rewards": -2.058667145742157,
    "random_rewards": -1.0616674928871968,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0179018318951765,
    "equal_rewards": -2.036039056161491,
    "random_rewards": -2.385561244660847,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0190211266933344,
    "equal_rewards": -2.037246837741544,
    "random_rewards": -1.4752661652522616,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0165201109730595,
    "equal_rewards": -2.064822722019813,
    "random_rewards": -1.8121998631245915,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.045506184744013,
    "equal_rewards": -2.0293996903280216,
    "random_rewards": -1.781911923214848,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9974402482243319,
    "equal_rewards": -2.0557675932991706,
    "random_rewards": -2.8438832810481984,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0275028224849585,
    "equal_rewards": -2.053021757558325,
    "random_rewards": -2.138778673333765,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0062236086687344,
    "equal_rewards": -2.062031885120051,
    "random_rewards": -1.6674260656212694,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0422556074355778,
    "equal_rewards": -2.026579772264909,
    "random_rewards": -1.485082872922273,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0593412244642324,
    "equal_rewards": -2.03117577719543,
    "random_rewards": -1.3400910361124203,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0200789700382056,
    "equal_rewards": -2.074828051090817,
    "random_rewards": -1.8381597987515714,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.008878505100485,
    "equal_rewards": -2.0632012546392025,
    "random_rewards": -1.6366660777843425,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.034300014655691,
    "equal_rewards": -2.0262448900634054,
    "random_rewards": -0.44478546367245475,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.977912047502291,
    "equal_rewards": -2.0311417746850227,
    "random_rewards": -1.7917531622719716,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0124696483274933,
    "equal_rewards": -2.0417042603881717,
    "random_rewards": -1.817382639876787,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.002999073482036,
    "equal_rewards": -2.057146125874892,
    "random_rewards": -2.8451764331949003,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0211530734813645,
    "equal_rewards": -2.051790497244007,
    "random_rewards": -1.3504144233444395,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.006552729703363,
    "equal_rewards": -2.0572765029767828,
    "random_rewards": -1.2038624435923704,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0050707277587625,
    "equal_rewards": -2.05456503329944,
    "random_rewards": -1.8257997360034564,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.051215892398419,
    "equal_rewards": -2.011012560982673,
    "random_rewards": -1.4834525922449349,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0047721300893784,
    "equal_rewards": -2.0573638262622276,
    "random_rewards": -2.387331624030698,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0022792166571572,
    "equal_rewards": -2.060343501152333,
    "random_rewards": -1.7986925395169142,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0189117479900096,
    "equal_rewards": -2.0390674962185136,
    "random_rewards": -1.7677179337177915,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9911680650919859,
    "equal_rewards": -2.0284088120654795,
    "random_rewards": -1.3570675696926822,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.993275029664705,
    "equal_rewards": -2.043576834457041,
    "random_rewards": -1.937400402752985,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0520450625969446,
    "equal_rewards": -2.0333111994302078,
    "random_rewards": -2.82481114061071,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0226433711443623,
    "equal_rewards": -2.0573906718193116,
    "random_rewards": -2.4012607589687134,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0063726135201865,
    "equal_rewards": -2.0589085197302817,
    "random_rewards": -1.8454424738884412,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013703533198589,
    "equal_rewards": -2.062025359633411,
    "random_rewards": -2.1190635940125953,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0126847165496233,
    "equal_rewards": -2.0546156588011955,
    "random_rewards": -1.6761037293405754,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0460318146580674,
    "equal_rewards": -2.0283507852035605,
    "random_rewards": -2.2129682425073396,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9868606079807989,
    "equal_rewards": -2.0505952733349013,
    "random_rewards": -1.1909337782109095,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.018936784274066,
    "equal_rewards": -2.0754980995695793,
    "random_rewards": -2.72516345913313,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.040366580222327,
    "equal_rewards": -2.0577475214836896,
    "random_rewards": -2.568766858633208,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0246959958150588,
    "equal_rewards": -2.0403354148186468,
    "random_rewards": -2.2326020835122584,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.002061255431837,
    "equal_rewards": -2.024165868659293,
    "random_rewards": -2.9617053600325716,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007905054821204,
    "equal_rewards": -1.9990419368517123,
    "random_rewards": -2.025575287478094,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0081050361647907,
    "equal_rewards": -2.0634496035969607,
    "random_rewards": -1.5103680658279601,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0389642792875358,
    "equal_rewards": -2.060234696182161,
    "random_rewards": -2.261233203126762,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0437112291093724,
    "equal_rewards": -2.027963875054863,
    "random_rewards": -1.4984041206914445,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007143839240041,
    "equal_rewards": -2.0594190917053883,
    "random_rewards": -1.7948606240492642,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0092599970861618,
    "equal_rewards": -2.0674347897677694,
    "random_rewards": -1.9524306426527351,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007173200486257,
    "equal_rewards": -2.0759840253580726,
    "random_rewards": -1.690757279636154,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.045957849501008,
    "equal_rewards": -2.066301512819709,
    "random_rewards": -2.2909001218099325,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0214337181334217,
    "equal_rewards": -2.082395710138023,
    "random_rewards": -2.4511712395346876,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.020480469020372,
    "equal_rewards": -2.071396525875099,
    "random_rewards": -0.8861581401528551,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.995933429139652,
    "equal_rewards": -2.048938211749076,
    "random_rewards": -1.1772621483211667,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9963241120789683,
    "equal_rewards": -2.0338152111439434,
    "random_rewards": -1.9473547927765211,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9943274804390188,
    "equal_rewards": -2.047705879779748,
    "random_rewards": -2.102327983255836,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0039497582359243,
    "equal_rewards": -2.063021061902317,
    "random_rewards": -2.2943339896437154,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0567134704247865,
    "equal_rewards": -2.019209396849897,
    "random_rewards": -1.1972958492569694,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0414491223701954,
    "equal_rewards": -2.021142104216648,
    "random_rewards": -1.6192861013154463,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9894777743753593,
    "equal_rewards": -2.045353506308416,
    "random_rewards": -2.066453874852315,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.056842230036304,
    "equal_rewards": -2.0213251778340267,
    "random_rewards": -2.0787815571829444,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0576176948626843,
    "equal_rewards": -2.0202275410189703,
    "random_rewards": -1.7491164450101087,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0062059421642866,
    "equal_rewards": -2.059539387969394,
    "random_rewards": -1.6886680643117582,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0275164492676216,
    "equal_rewards": -2.0540740974230953,
    "random_rewards": -2.09509052057937,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0211122572423648,
    "equal_rewards": -2.053982966781657,
    "random_rewards": -1.3532817128994439,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9953208359730867,
    "equal_rewards": -2.060971976757908,
    "random_rewards": -1.9239240109249365,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0467727624363152,
    "equal_rewards": -1.99890376134717,
    "random_rewards": -1.5001167511578155,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9594130048248888,
    "equal_rewards": -1.9351254244134135,
    "random_rewards": -1.389583759458157,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9286357633907136,
    "equal_rewards": -1.9799466152224086,
    "random_rewards": -1.7679163153115767,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9280370301499565,
    "equal_rewards": -1.971367410778622,
    "random_rewards": -2.1386089988286576,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9759198399550673,
    "equal_rewards": -2.0051338567627157,
    "random_rewards": -1.28601877195334,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9924967342068063,
    "equal_rewards": -2.052791220633054,
    "random_rewards": -1.216488275602929,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9854892712933592,
    "equal_rewards": -2.0472651895688063,
    "random_rewards": -1.97590658912784,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.032010018457024,
    "equal_rewards": -2.055207284529909,
    "random_rewards": -1.8066157069707454,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004276756842929,
    "equal_rewards": -2.069692913809406,
    "random_rewards": -1.217097228119085,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9924976059294093,
    "equal_rewards": -2.057414934817796,
    "random_rewards": -2.4185062909718176,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.032344409041313,
    "equal_rewards": -2.0144137589938045,
    "random_rewards": -2.066560223282433,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9795326910446822,
    "equal_rewards": -2.036931141815076,
    "random_rewards": -1.4684131204617548,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0118102329739385,
    "equal_rewards": -2.0346685290812174,
    "random_rewards": -1.7962094637412427,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0024606746089555,
    "equal_rewards": -2.0295117698526477,
    "random_rewards": -2.1857836888841753,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9361835739545448,
    "equal_rewards": -1.9232052891883162,
    "random_rewards": -1.9544272282220998,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8876691494012163,
    "equal_rewards": -1.876452706131591,
    "random_rewards": -0.6920835285041629,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9478368231097052,
    "equal_rewards": -1.9942446282241106,
    "random_rewards": -2.49878961586818,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.941475901630661,
    "equal_rewards": -1.966620720189837,
    "random_rewards": -2.590183387567102,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.938719470004784,
    "equal_rewards": -1.9601956902795352,
    "random_rewards": -1.901785548377092,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9698455872667497,
    "equal_rewards": -2.0238082957228016,
    "random_rewards": -2.259974089846132,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.957074731260834,
    "equal_rewards": -2.022302247739965,
    "random_rewards": -1.600397907984878,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8985020140327864,
    "equal_rewards": -1.963398537891664,
    "random_rewards": -1.8563805618881752,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9213589362115855,
    "equal_rewards": -1.9625600844847804,
    "random_rewards": -1.2524197597143765,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.019599818349675,
    "equal_rewards": -2.0000996685381853,
    "random_rewards": -1.4486155666296672,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.953660029650313,
    "equal_rewards": -1.96775519765862,
    "random_rewards": -2.321725021750212,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8955848052619526,
    "equal_rewards": -1.9467377685672975,
    "random_rewards": -1.2532245008557932,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8965576402812263,
    "equal_rewards": -1.9320699997248019,
    "random_rewards": -2.8333693825705577,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9739746737373736,
    "equal_rewards": -1.999309773297754,
    "random_rewards": -2.208615378829517,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9124897085965797,
    "equal_rewards": -1.9532188940512252,
    "random_rewards": -2.1119018202306363,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8627068412351107,
    "equal_rewards": -1.9099476114483684,
    "random_rewards": -2.093207449493695,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9629123014719179,
    "equal_rewards": -1.9898117124191188,
    "random_rewards": -2.1982423837162908,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9446973267751004,
    "equal_rewards": -1.97501964865895,
    "random_rewards": -1.3155227565739138,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.959240143161614,
    "equal_rewards": -1.9949094835778198,
    "random_rewards": -1.8906307830497333,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9306843358308479,
    "equal_rewards": -1.9888009359025234,
    "random_rewards": -2.2907573686046097,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9702575520782855,
    "equal_rewards": -1.9871866036176014,
    "random_rewards": -2.308613624469488,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.941839780631271,
    "equal_rewards": -1.97018149985044,
    "random_rewards": -2.603563013308487,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9027381145573314,
    "equal_rewards": -1.937854380565014,
    "random_rewards": -2.26764515462302,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8829197113361715,
    "equal_rewards": -1.9480987540014532,
    "random_rewards": -1.7247888535234182,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.00117053327507,
    "equal_rewards": -1.9659722278918763,
    "random_rewards": -2.7413767645721165,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.001626181967991,
    "equal_rewards": -2.0552774824464475,
    "random_rewards": -2.252837667174444,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9911490267916225,
    "equal_rewards": -2.0501091093605703,
    "random_rewards": -1.9188356832799238,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000493080256208,
    "equal_rewards": -2.0556614456435516,
    "random_rewards": -1.8370346476538637,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.97018016715611,
    "equal_rewards": -1.9945827532870337,
    "random_rewards": -2.2049780027360146,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.955809395806689,
    "equal_rewards": -1.9353688558995659,
    "random_rewards": -2.2932795101925216,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.895171084250069,
    "equal_rewards": -1.9558580375715184,
    "random_rewards": -2.0389969608475464,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.002926025749352,
    "equal_rewards": -1.9724200703571397,
    "random_rewards": -1.3042715359600061,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.01428571477002,
    "equal_rewards": -2.0027779799180907,
    "random_rewards": -2.015506820414482,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9697408897970508,
    "equal_rewards": -1.993757067091366,
    "random_rewards": -2.008801276861647,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.837836474352894,
    "equal_rewards": -1.89590144427455,
    "random_rewards": -1.632099269929359,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9185191823678567,
    "equal_rewards": -1.8894462184696654,
    "random_rewards": -1.923794075984714,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0120088671990275,
    "equal_rewards": -2.0357142253310885,
    "random_rewards": -1.5130037490262547,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9935570854723186,
    "equal_rewards": -2.0458159853097087,
    "random_rewards": -2.709187162084736,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.998115769424168,
    "equal_rewards": -2.049387871550045,
    "random_rewards": -2.098175431940316,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0004741373756323,
    "equal_rewards": -2.050458121105626,
    "random_rewards": -1.477965952937644,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0277307010835117,
    "equal_rewards": -2.0112570971287775,
    "random_rewards": -1.4726848528695338,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9698998306083235,
    "equal_rewards": -2.0373341464008634,
    "random_rewards": -1.204827543555262,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9884009970542076,
    "equal_rewards": -2.0434910729326585,
    "random_rewards": -1.0386517973645157,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9870390171191903,
    "equal_rewards": -2.034456621370615,
    "random_rewards": -1.8103724770605387,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9846810006376825,
    "equal_rewards": -2.04961152965882,
    "random_rewards": -2.2974069764560343,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.98663594375907,
    "equal_rewards": -2.0508461433730063,
    "random_rewards": -1.3866475674740044,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9858079588419075,
    "equal_rewards": -2.049199020974708,
    "random_rewards": -2.5202416513649073,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9622810134600623,
    "equal_rewards": -2.013483706125599,
    "random_rewards": -2.3960425636257154,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9956163485275904,
    "equal_rewards": -2.0187587478391475,
    "random_rewards": -1.7641930106067898,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9993718280240698,
    "equal_rewards": -2.053260301701279,
    "random_rewards": -2.080797857901713,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9847288052964747,
    "equal_rewards": -2.0334308192365027,
    "random_rewards": -2.5219471562901075,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.997844206175881,
    "equal_rewards": -2.0182295063864997,
    "random_rewards": -1.459387832814842,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0214194329536936,
    "equal_rewards": -1.9928193810586603,
    "random_rewards": -2.177328710664785,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.960066551656987,
    "equal_rewards": -2.01629637321094,
    "random_rewards": -1.1658883215811475,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.982809762712522,
    "equal_rewards": -1.9651357510584777,
    "random_rewards": -1.4566251609244805,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9539025391248188,
    "equal_rewards": -2.0048364650985526,
    "random_rewards": -2.92661257903827,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.993047629838839,
    "equal_rewards": -2.0152800574501186,
    "random_rewards": -1.4899517884783322,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9764258706470712,
    "equal_rewards": -2.0443568165101493,
    "random_rewards": -2.111092057206639,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8692029054913586,
    "equal_rewards": -1.9303086624784442,
    "random_rewards": -1.529142058039891,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8209522722676992,
    "equal_rewards": -1.796573460431456,
    "random_rewards": -0.9201300038196929,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9564381282851202,
    "equal_rewards": -1.9299435571493884,
    "random_rewards": -0.9808825555911405,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0356852207208087,
    "equal_rewards": -2.0186955815318273,
    "random_rewards": -2.2265683272621457,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9773259011005895,
    "equal_rewards": -2.0134092350293695,
    "random_rewards": -1.4806892516555996,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016932612659133,
    "equal_rewards": -1.9926118183551162,
    "random_rewards": -1.6219742463506341,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9830814063664255,
    "equal_rewards": -2.0484428834568016,
    "random_rewards": -1.6452517299516418,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9700859669294506,
    "equal_rewards": -2.0334038161349044,
    "random_rewards": -1.3600122215032726,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0025127019971647,
    "equal_rewards": -2.053202329315168,
    "random_rewards": -2.257182761932608,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016039499931519,
    "equal_rewards": -2.044862281575229,
    "random_rewards": -2.5668408438954238,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9524162500311715,
    "equal_rewards": -2.0125433438841176,
    "random_rewards": -1.1717136103616856,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9617932094214405,
    "equal_rewards": -2.0159675163810014,
    "random_rewards": -1.3495513332167999,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0046359153919875,
    "equal_rewards": -2.0310235316957974,
    "random_rewards": -1.8057266064359887,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0065098618446595,
    "equal_rewards": -2.0355589944974506,
    "random_rewards": -1.466796965910755,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9719194851603445,
    "equal_rewards": -2.0319875397810936,
    "random_rewards": -1.5035645650694647,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.987419592493945,
    "equal_rewards": -2.010119901567608,
    "random_rewards": -1.3010832777352943,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.929124132061833,
    "equal_rewards": -1.9935799005904797,
    "random_rewards": -2.3279669240388348,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.953763376304536,
    "equal_rewards": -1.9804649687043843,
    "random_rewards": -2.3411191908490294,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9521376230268817,
    "equal_rewards": -2.007657891483701,
    "random_rewards": -1.4382447813614103,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9762720996814278,
    "equal_rewards": -2.017002049116307,
    "random_rewards": -1.4833278316250904,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9795385220370922,
    "equal_rewards": -1.9882648503853764,
    "random_rewards": -2.319987880621836,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9725801556029232,
    "equal_rewards": -2.0260139351099653,
    "random_rewards": -2.1868277452618807,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0439135748831845,
    "equal_rewards": -2.0203320179861097,
    "random_rewards": -1.9338615593005581,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.967634364343167,
    "equal_rewards": -2.0466017496611038,
    "random_rewards": -2.084233509138336,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.964782779876555,
    "equal_rewards": -1.9917368550475592,
    "random_rewards": -1.8789119733317532,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9439059083375885,
    "equal_rewards": -1.9997406113488645,
    "random_rewards": -1.7558698050868078,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.947921378035882,
    "equal_rewards": -2.0024401011968904,
    "random_rewards": -1.3562727113493773,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9455225727947338,
    "equal_rewards": -2.009111502625616,
    "random_rewards": -1.0030915172235058,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9549609295632147,
    "equal_rewards": -2.000589622578047,
    "random_rewards": -2.193358109699958,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9655720624790705,
    "equal_rewards": -2.0214171035117703,
    "random_rewards": -2.0474804421687764,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0131074080381417,
    "equal_rewards": -1.9994033550111783,
    "random_rewards": -2.1799249007123884,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9244168499469425,
    "equal_rewards": -1.9778950638021557,
    "random_rewards": -1.3193990134003672,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9474737883461706,
    "equal_rewards": -2.012482373618714,
    "random_rewards": -0.720394150404414,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.006798552762814,
    "equal_rewards": -2.0260837869050166,
    "random_rewards": -2.2608365071549734,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0129738642632464,
    "equal_rewards": -1.9987154933130036,
    "random_rewards": -1.4610331104107974,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.04668100694252,
    "equal_rewards": -2.014534719595277,
    "random_rewards": -2.2335159511885956,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9578649320472177,
    "equal_rewards": -2.0213246747909372,
    "random_rewards": -2.532435902865736,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.968030183035587,
    "equal_rewards": -2.024335575750648,
    "random_rewards": -1.0375168621393973,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9891483446236933,
    "equal_rewards": -2.0432937735755394,
    "random_rewards": -2.122912188877269,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0109305293311657,
    "equal_rewards": -2.0385412414946664,
    "random_rewards": -1.7899386510684874,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.014393941343945,
    "equal_rewards": -2.0229316346867106,
    "random_rewards": -0.585778021381574,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9559573601085725,
    "equal_rewards": -2.018604930104151,
    "random_rewards": -2.1002919008644634,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9780965223376346,
    "equal_rewards": -1.9406758191212357,
    "random_rewards": -2.158450523881718,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9427876799527823,
    "equal_rewards": -2.003429228008776,
    "random_rewards": -2.3269028384438553,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9551415206896854,
    "equal_rewards": -2.0039643270310155,
    "random_rewards": -1.5971285705751885,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9731730537089531,
    "equal_rewards": -1.9704959266950195,
    "random_rewards": -1.7425077338252613,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9737934925932343,
    "equal_rewards": -1.999225529590169,
    "random_rewards": -2.021974859747603,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9609961191448932,
    "equal_rewards": -2.0194476146299443,
    "random_rewards": -1.1684907658160522,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.993681848726065,
    "equal_rewards": -2.0470697040321704,
    "random_rewards": -1.647285207166087,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9751627972166832,
    "equal_rewards": -2.031530770493501,
    "random_rewards": -1.4860325963527394,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.972651778490182,
    "equal_rewards": -2.01662584340252,
    "random_rewards": -1.0435521444783726,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9631645375587798,
    "equal_rewards": -2.0285936473000548,
    "random_rewards": -0.8630860537084893,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9715742845433586,
    "equal_rewards": -2.0185783006937696,
    "random_rewards": -1.0664454881796297,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.049071052875964,
    "equal_rewards": -2.0059236618645726,
    "random_rewards": -2.3521501358401813,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0131060485527077,
    "equal_rewards": -2.0356054855097523,
    "random_rewards": -0.902039354347532,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9457781293888754,
    "equal_rewards": -2.0169945254318185,
    "random_rewards": -1.7376663042270462,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0166427965577514,
    "equal_rewards": -1.9932201311527873,
    "random_rewards": -2.7754324864979516,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.001574401870023,
    "equal_rewards": -2.0272135492603223,
    "random_rewards": -1.0392360238005305,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9920960547510052,
    "equal_rewards": -2.0184654164733895,
    "random_rewards": -1.196807166178371,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9821916495435468,
    "equal_rewards": -2.042906583310555,
    "random_rewards": -1.6434976800436154,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9755655366014029,
    "equal_rewards": -2.0323110237088553,
    "random_rewards": -1.7946701454890839,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9927408146165644,
    "equal_rewards": -2.0260880749571513,
    "random_rewards": -2.4979778687504286,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9835909982618505,
    "equal_rewards": -2.0363260477432803,
    "random_rewards": -1.960298754028167,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0177776652978228,
    "equal_rewards": -2.0131785560902817,
    "random_rewards": -1.306021376632686,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0011299180889477,
    "equal_rewards": -2.0277732343311716,
    "random_rewards": -1.8920367804680063,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9951870440030626,
    "equal_rewards": -2.042537817488673,
    "random_rewards": -1.6749836998652519,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021258571126628,
    "equal_rewards": -2.009335910201867,
    "random_rewards": -1.3279640853708552,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9383825637627297,
    "equal_rewards": -1.9972162534697526,
    "random_rewards": -1.4555990443173956,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9108949183553623,
    "equal_rewards": -1.9680154581923135,
    "random_rewards": -2.199169292524924,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9353724748696948,
    "equal_rewards": -1.9796965197876037,
    "random_rewards": -1.7515777266483008,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9280654229691483,
    "equal_rewards": -1.9877201173406713,
    "random_rewards": -2.1950024687187204,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9980047971282051,
    "equal_rewards": -2.0269344086308956,
    "random_rewards": -1.2091174131028473,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9930583312454206,
    "equal_rewards": -2.0497802832421823,
    "random_rewards": -1.943821931594929,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9717436023924222,
    "equal_rewards": -2.0266073107972744,
    "random_rewards": -0.8990405031806116,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9562349417063736,
    "equal_rewards": -2.0064900496665623,
    "random_rewards": -2.156313694382462,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9705801034387913,
    "equal_rewards": -2.015676634703671,
    "random_rewards": -2.1627078870973735,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.01204626908877,
    "equal_rewards": -1.9761549014712672,
    "random_rewards": -1.7050056532401863,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0005882985373855,
    "equal_rewards": -1.985331728383551,
    "random_rewards": -2.1992076309407933,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9791650336849982,
    "equal_rewards": -2.0337857127136068,
    "random_rewards": -2.05912190340546,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9915859337697404,
    "equal_rewards": -2.0481633059578925,
    "random_rewards": -2.119308954027381,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9877745476804398,
    "equal_rewards": -2.037470414977916,
    "random_rewards": -1.1943581785201554,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0149163262078167,
    "equal_rewards": -2.0360602703826873,
    "random_rewards": -0.5888986678799548,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010102669638643,
    "equal_rewards": -2.0595137990251398,
    "random_rewards": -3.013649935821131,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9964020638901454,
    "equal_rewards": -2.0504112508007246,
    "random_rewards": -1.453801082957173,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.989643274852484,
    "equal_rewards": -2.054722619197263,
    "random_rewards": -2.1013163797963346,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9948160354251803,
    "equal_rewards": -2.038084625663039,
    "random_rewards": -1.487955936009295,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9903889382128581,
    "equal_rewards": -2.013665482838933,
    "random_rewards": -2.2341872048947344,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0090877107876257,
    "equal_rewards": -1.9736731511869445,
    "random_rewards": -1.7196245109041464,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9589730091238016,
    "equal_rewards": -1.9901104432537293,
    "random_rewards": -1.46730441921887,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9784034757000348,
    "equal_rewards": -2.0307237546228274,
    "random_rewards": -1.018874033213222,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.017488980426255,
    "equal_rewards": -2.0435552212151613,
    "random_rewards": -2.5569854640206118,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0140315613972075,
    "equal_rewards": -2.033772570573946,
    "random_rewards": -1.1752380775179887,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9788076709063027,
    "equal_rewards": -2.0326230672412064,
    "random_rewards": -0.9075066829104529,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.002253130434807,
    "equal_rewards": -2.0240286440634896,
    "random_rewards": -2.8206637934852905,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9942878376202329,
    "equal_rewards": -2.0267907799564733,
    "random_rewards": -1.7714918025598883,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.039971827920102,
    "equal_rewards": -2.0274840596923562,
    "random_rewards": -2.3502368704012633,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.042125089238067,
    "equal_rewards": -2.0258414370496585,
    "random_rewards": -2.056355874245897,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9888278950983656,
    "equal_rewards": -2.047777907544026,
    "random_rewards": -1.980118318502367,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0125216645856288,
    "equal_rewards": -2.037540770695211,
    "random_rewards": -1.334975716021322,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9941407087356007,
    "equal_rewards": -2.0575553965625852,
    "random_rewards": -0.45165850168446997,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0102238122996074,
    "equal_rewards": -2.0402316504301967,
    "random_rewards": -1.0382336218208936,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.983305103215192,
    "equal_rewards": -2.049011131809646,
    "random_rewards": -1.0572301667045951,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007524987909413,
    "equal_rewards": -2.0327122108546316,
    "random_rewards": -1.6433762845102844,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0148768134303205,
    "equal_rewards": -2.0441468839528114,
    "random_rewards": -1.767696479076982,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9966056342915293,
    "equal_rewards": -2.0506769697460925,
    "random_rewards": -2.5367891354115217,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9910720779116646,
    "equal_rewards": -2.0442883783081216,
    "random_rewards": -1.9746407469941347,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.999359406644668,
    "equal_rewards": -2.024132214037709,
    "random_rewards": -1.4502600939600951,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.042512480797126,
    "equal_rewards": -2.0240149635660236,
    "random_rewards": -1.6314843628532587,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9942419265566957,
    "equal_rewards": -2.0498375598050336,
    "random_rewards": -2.107930863377265,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9767827942924434,
    "equal_rewards": -2.0314833369131726,
    "random_rewards": -2.0909657623044824,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0169228620898876,
    "equal_rewards": -2.040346854567065,
    "random_rewards": -2.266642526599628,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9970365471280558,
    "equal_rewards": -2.0332733724848806,
    "random_rewards": -1.347113308538821,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.978678396479303,
    "equal_rewards": -1.998468860222585,
    "random_rewards": -1.0515951011086344,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9739808238855443,
    "equal_rewards": -2.0278004899489828,
    "random_rewards": -0.7346003586532825,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.025808159326272,
    "equal_rewards": -2.0744955422490805,
    "random_rewards": -1.9807417155959457,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9929753445818883,
    "equal_rewards": -2.0644310019104823,
    "random_rewards": -2.5730930241048813,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004251918189452,
    "equal_rewards": -2.034843969177604,
    "random_rewards": -1.6532922606959861,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9867967368041304,
    "equal_rewards": -2.0280158291327144,
    "random_rewards": -2.539173050292735,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9700159194121176,
    "equal_rewards": -2.032112807246846,
    "random_rewards": -1.7957630856474802,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007876537961743,
    "equal_rewards": -1.98983440298558,
    "random_rewards": -3.0575504240997935,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9892421622469052,
    "equal_rewards": -2.0141040273307915,
    "random_rewards": -2.490219580059827,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9782591910008112,
    "equal_rewards": -2.039671371300995,
    "random_rewards": -1.9810192677001504,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9664568527488968,
    "equal_rewards": -1.9988039807596432,
    "random_rewards": -1.2900920334414976,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9067160743935687,
    "equal_rewards": -1.9643068226267024,
    "random_rewards": -1.4451738682979423,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.001264193874894,
    "equal_rewards": -1.9874949668159008,
    "random_rewards": -1.7273804397542767,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9808605908925916,
    "equal_rewards": -2.043400065936863,
    "random_rewards": -1.0292259270420265,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0091017073249544,
    "equal_rewards": -2.0020730128416124,
    "random_rewards": -1.8751980761786657,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0253607230883963,
    "equal_rewards": -2.0442279987851757,
    "random_rewards": -2.2436648767154366,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9845014754898265,
    "equal_rewards": -2.046842227369169,
    "random_rewards": -1.82914425825241,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9829325452262916,
    "equal_rewards": -2.037743101598415,
    "random_rewards": -1.8213025952199648,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9846595672020702,
    "equal_rewards": -2.0099335382452677,
    "random_rewards": -0.8824098460588978,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9600699043645222,
    "equal_rewards": -2.017175528019262,
    "random_rewards": -1.6213277649595028,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.991060082528692,
    "equal_rewards": -2.0415928528776583,
    "random_rewards": -1.4783774074950746,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9965480619985607,
    "equal_rewards": -2.029164084357886,
    "random_rewards": -1.6136631263996084,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0025727930075257,
    "equal_rewards": -2.0575213125109015,
    "random_rewards": -1.4996581828557427,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0186238339959566,
    "equal_rewards": -2.030016740255869,
    "random_rewards": -2.2565380172022715,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0332617430510433,
    "equal_rewards": -2.0022986813251844,
    "random_rewards": -1.7750815109468725,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9757943870363364,
    "equal_rewards": -2.0250456220702384,
    "random_rewards": -1.0533044808519352,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9894407545504793,
    "equal_rewards": -2.037506868522173,
    "random_rewards": -1.7677170920871599,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0385933385603656,
    "equal_rewards": -2.0233144683316984,
    "random_rewards": -0.8983775215822699,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9858069705667398,
    "equal_rewards": -2.03927102903971,
    "random_rewards": -2.0529893992578176,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.98025477755364,
    "equal_rewards": -2.0488221021949844,
    "random_rewards": -1.0616719069839489,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9925042837489515,
    "equal_rewards": -2.043214434551807,
    "random_rewards": -1.9568035595971423,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9877493505564026,
    "equal_rewards": -2.0049957774184684,
    "random_rewards": -1.8860181630597392,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.003751781584012,
    "equal_rewards": -2.0534667407108773,
    "random_rewards": -1.51110384194192,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.003456814402953,
    "equal_rewards": -2.056370811902245,
    "random_rewards": -2.693508763635549,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0064349103410333,
    "equal_rewards": -2.0287755185689607,
    "random_rewards": -2.8064240281783612,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9847592959697344,
    "equal_rewards": -2.031088864001595,
    "random_rewards": -1.4631834181103276,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0075760766459707,
    "equal_rewards": -2.0607189727464466,
    "random_rewards": -2.218325556437331,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.030251908062046,
    "equal_rewards": -2.0211256610823005,
    "random_rewards": -1.7477108396478143,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9815988021819617,
    "equal_rewards": -2.0362376995890754,
    "random_rewards": -1.5013443760537923,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.997469291498418,
    "equal_rewards": -2.0623645569964406,
    "random_rewards": -1.9952015571296793,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0151786514408068,
    "equal_rewards": -2.0440711677199257,
    "random_rewards": -0.8964578585775222,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0201335610336106,
    "equal_rewards": -2.0046553206498077,
    "random_rewards": -2.926885782843191,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9972881117334071,
    "equal_rewards": -2.051640108804899,
    "random_rewards": -0.7432552631905058,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0015448403068428,
    "equal_rewards": -2.0571380246390185,
    "random_rewards": -1.6765854731711136,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.03595402865193,
    "equal_rewards": -2.059743305341078,
    "random_rewards": -1.9455341039344465,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9975710848068018,
    "equal_rewards": -2.067896280759863,
    "random_rewards": -1.3745261358202407,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9944256801979967,
    "equal_rewards": -2.0192234365259143,
    "random_rewards": -1.880536243066114,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.978055059681253,
    "equal_rewards": -2.003144363111944,
    "random_rewards": -2.630177498374242,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0029319223884112,
    "equal_rewards": -2.05539562306705,
    "random_rewards": -1.534094491779006,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0238363092799654,
    "equal_rewards": -2.0095630407499954,
    "random_rewards": -1.8989563473028248,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9613772799141844,
    "equal_rewards": -2.0266386599593527,
    "random_rewards": -1.4813649859311955,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000923853483421,
    "equal_rewards": -2.0638952418909957,
    "random_rewards": -1.9416092623439583,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.032583239771852,
    "equal_rewards": -2.0478139268611746,
    "random_rewards": -1.4612466221690212,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0332770380423737,
    "equal_rewards": -2.004323121303824,
    "random_rewards": -1.6080248221101656,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0028066900350243,
    "equal_rewards": -2.028879669360234,
    "random_rewards": -1.7952282271377344,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0008617043125563,
    "equal_rewards": -2.026291698636595,
    "random_rewards": -1.6258776673459185,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.003971609728233,
    "equal_rewards": -2.06043084053333,
    "random_rewards": -2.218241332492477,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.006117640498323,
    "equal_rewards": -2.0611858149457936,
    "random_rewards": -2.4290174159474676,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.026079562452697,
    "equal_rewards": -2.0480290382452724,
    "random_rewards": -1.6650901338213815,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0343800646123147,
    "equal_rewards": -2.0182609348702565,
    "random_rewards": -1.6297962626926088,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.988431366428347,
    "equal_rewards": -2.0412738003828057,
    "random_rewards": -2.1052977618632736,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9779992563169149,
    "equal_rewards": -2.0502647874943407,
    "random_rewards": -1.9690910834034656,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013815416884407,
    "equal_rewards": -2.0425394136091346,
    "random_rewards": -1.4646551880326548,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9850975201534053,
    "equal_rewards": -2.043628638103022,
    "random_rewards": -2.247596953142298,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.026027931447042,
    "equal_rewards": -2.0229194787455755,
    "random_rewards": -2.360827408428076,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9940743018106026,
    "equal_rewards": -2.047258641980985,
    "random_rewards": -2.524394974839848,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9925657520650084,
    "equal_rewards": -2.0440157057638784,
    "random_rewards": -2.1238443826667557,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9906704731028317,
    "equal_rewards": -2.0342334077531508,
    "random_rewards": -2.8355907185616145,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9798735859550258,
    "equal_rewards": -2.0209930779114713,
    "random_rewards": -1.4681344143279533,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.997183945917835,
    "equal_rewards": -1.9852419668395043,
    "random_rewards": -1.732763943816043,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9724188914331062,
    "equal_rewards": -2.028081741644779,
    "random_rewards": -1.9337678837069496,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9670504651428378,
    "equal_rewards": -1.99795679131699,
    "random_rewards": -1.7623202655173995,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9779390926769314,
    "equal_rewards": -2.0298166377718214,
    "random_rewards": -1.0110496142775167,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9672129708280928,
    "equal_rewards": -2.029476206013937,
    "random_rewards": -2.2424285218672675,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9420986831026514,
    "equal_rewards": -1.9974276709259957,
    "random_rewards": -2.054011729495085,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9925788272357496,
    "equal_rewards": -2.0040337839230022,
    "random_rewards": -0.7327042790234441,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9825122336104661,
    "equal_rewards": -2.0291455518798514,
    "random_rewards": -1.38165275341016,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.987774686134638,
    "equal_rewards": -2.0500878493603474,
    "random_rewards": -1.6730826861450416,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.04240404945523,
    "equal_rewards": -2.022610355397148,
    "random_rewards": -2.243674479866683,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.02206289541676,
    "equal_rewards": -2.0426770397895466,
    "random_rewards": -2.4115242473960095,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0196123035855744,
    "equal_rewards": -2.04601945834932,
    "random_rewards": -1.501710892378014,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000341830477361,
    "equal_rewards": -2.054455806173487,
    "random_rewards": -2.2109130817120786,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9824686389383066,
    "equal_rewards": -2.035971733264217,
    "random_rewards": -0.7459204201905569,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9855560500269738,
    "equal_rewards": -2.0449429434789446,
    "random_rewards": -1.3721299680805836,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.985807806876644,
    "equal_rewards": -2.0462899364553544,
    "random_rewards": -1.763413538264904,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004739442826164,
    "equal_rewards": -2.0327042534097535,
    "random_rewards": -2.83366348703138,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9949162171244341,
    "equal_rewards": -2.049516313822529,
    "random_rewards": -1.9660617024491605,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9882120647304367,
    "equal_rewards": -2.041977747427911,
    "random_rewards": -0.604947740603363,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.019335565005402,
    "equal_rewards": -1.9859246295249955,
    "random_rewards": -1.877127637387237,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9650699941624326,
    "equal_rewards": -1.9919690597721746,
    "random_rewards": -1.3432040825449314,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9772172388682998,
    "equal_rewards": -2.0328220490102518,
    "random_rewards": -1.345021033285927,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0025081306918717,
    "equal_rewards": -1.9813959822792642,
    "random_rewards": -2.200986078081087,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9989498617278223,
    "equal_rewards": -2.021051940141497,
    "random_rewards": -2.8085276206986913,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.022231489318503,
    "equal_rewards": -2.046710903699571,
    "random_rewards": -1.7681075306002403,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9774230597166105,
    "equal_rewards": -2.0376559991188805,
    "random_rewards": -1.8057758790550884,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013056209482677,
    "equal_rewards": -2.0235921025531627,
    "random_rewards": -1.3147193141138178,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9993104545496843,
    "equal_rewards": -2.065783704958325,
    "random_rewards": -1.8372436632383722,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.005774090470409,
    "equal_rewards": -2.0597715117840982,
    "random_rewards": -0.4521449660013874,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9912221256795726,
    "equal_rewards": -2.05218664645238,
    "random_rewards": -0.8922864846513213,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9821930344777106,
    "equal_rewards": -2.035366809874839,
    "random_rewards": -1.3411916555957428,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9644773405627962,
    "equal_rewards": -2.0170481321314533,
    "random_rewards": -2.6350967434696932,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9782820682946674,
    "equal_rewards": -2.0315141190092643,
    "random_rewards": -2.840537732165222,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0075124168824163,
    "equal_rewards": -2.005044517117105,
    "random_rewards": -1.020778468511132,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0315001957388876,
    "equal_rewards": -2.0149176644816205,
    "random_rewards": -1.8857682387335346,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9965573045738998,
    "equal_rewards": -2.0536037259980704,
    "random_rewards": -1.1869137493678528,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0509086243075165,
    "equal_rewards": -2.0338130446814437,
    "random_rewards": -2.233286994131084,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9537609200722366,
    "equal_rewards": -1.973916846488403,
    "random_rewards": -1.2930535923519328,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9664442002097817,
    "equal_rewards": -1.9480762467434403,
    "random_rewards": -1.4173542166925999,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.002943756249655,
    "equal_rewards": -2.0121379688579584,
    "random_rewards": -2.0710557644468683,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9492249446617156,
    "equal_rewards": -1.9974312888103136,
    "random_rewards": -2.652367448670071,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9890532372978669,
    "equal_rewards": -1.9750975718488415,
    "random_rewards": -1.4478870389844696,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.006199055869665,
    "equal_rewards": -2.051752745620954,
    "random_rewards": -1.7706308791673355,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.985709061729445,
    "equal_rewards": -2.0451986971625553,
    "random_rewards": -2.2447302773735363,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9718826700044354,
    "equal_rewards": -2.0104179257114225,
    "random_rewards": -1.4850561795811055,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9833293856670924,
    "equal_rewards": -2.005256639887216,
    "random_rewards": -1.9378402970925153,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9777437476371251,
    "equal_rewards": -1.9881289408356357,
    "random_rewards": -1.6140895671389437,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9801919018488838,
    "equal_rewards": -2.0252969222927284,
    "random_rewards": -1.7921767803494155,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013485011637855,
    "equal_rewards": -2.033317812594854,
    "random_rewards": -1.3092302770594173,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004121540994848,
    "equal_rewards": -2.0252955459717668,
    "random_rewards": -1.3430042687594597,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.048442301411327,
    "equal_rewards": -2.0211853609865518,
    "random_rewards": -2.3592514604918224,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0293999299261367,
    "equal_rewards": -2.0221809853308166,
    "random_rewards": -2.6552007610960118,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0517466620665163,
    "equal_rewards": -2.026190930986954,
    "random_rewards": -2.81669226820031,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9954186696868623,
    "equal_rewards": -2.0056897586622333,
    "random_rewards": -1.3282108042306493,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9960188110449248,
    "equal_rewards": -2.028662921795905,
    "random_rewards": -1.6095237611510242,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.023730889165634,
    "equal_rewards": -2.0405465009476944,
    "random_rewards": -2.0783741284522415,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.045252358437143,
    "equal_rewards": -2.0203038761599657,
    "random_rewards": -1.7778516777280045,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9955452026934328,
    "equal_rewards": -2.046074837072423,
    "random_rewards": -1.6686754089622868,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.043026428435741,
    "equal_rewards": -2.007818213356698,
    "random_rewards": -2.05712404123266,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0148933937224314,
    "equal_rewards": -2.0186261522883293,
    "random_rewards": -1.0396923192203709,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9971821730671928,
    "equal_rewards": -2.0076098162533538,
    "random_rewards": -1.762779350856603,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9983470165301314,
    "equal_rewards": -2.0306992592679443,
    "random_rewards": -2.0649151072268768,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.014551379433357,
    "equal_rewards": -2.031211273726162,
    "random_rewards": -1.0338543749155256,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.024437651730839,
    "equal_rewards": -2.019882653623653,
    "random_rewards": -2.8147808072902025,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0570148670891593,
    "equal_rewards": -2.029349768306651,
    "random_rewards": -1.3462623979396007,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9915181241984907,
    "equal_rewards": -2.0240233961264584,
    "random_rewards": -1.9099123971257836,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0157542161738404,
    "equal_rewards": -2.040395841483882,
    "random_rewards": -1.9777410793889487,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0516656894765646,
    "equal_rewards": -2.046250488229811,
    "random_rewards": -1.3655719648824907,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0194314678226726,
    "equal_rewards": -2.027168691321238,
    "random_rewards": -1.1655403070589374,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.039247945976145,
    "equal_rewards": -1.9984068768909604,
    "random_rewards": -1.9308289009807453,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0170078614895357,
    "equal_rewards": -2.04964045128936,
    "random_rewards": -0.449921074673274,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.020160997607194,
    "equal_rewards": -2.00444062755592,
    "random_rewards": -2.0669630438987516,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.01045673390182,
    "equal_rewards": -2.0373991749051346,
    "random_rewards": -1.6778462505093967,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0090698565617635,
    "equal_rewards": -2.0378034145007744,
    "random_rewards": -2.090532085404373,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0399843454518023,
    "equal_rewards": -2.005445147136582,
    "random_rewards": -2.3533245596810297,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0219674218535895,
    "equal_rewards": -2.0399490984757342,
    "random_rewards": -1.499970239964502,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.029075787115589,
    "equal_rewards": -2.023179566803526,
    "random_rewards": -2.5044441729411244,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007280986266194,
    "equal_rewards": -2.058370589890369,
    "random_rewards": -0.8966807171325324,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0247212273485222,
    "equal_rewards": -2.0320606096067313,
    "random_rewards": -1.3314478277959303,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0353978387992777,
    "equal_rewards": -1.9983613371517417,
    "random_rewards": -1.6161758975041973,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0050847693453253,
    "equal_rewards": -2.0419919128980273,
    "random_rewards": -1.06739341628105,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0087186844775893,
    "equal_rewards": -2.026144022442757,
    "random_rewards": -1.9403091210991033,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0185980567780613,
    "equal_rewards": -2.0535935464738633,
    "random_rewards": -1.6836940855110845,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0613730494852436,
    "equal_rewards": -2.0209701781926874,
    "random_rewards": -0.8776170332693443,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0337084624226422,
    "equal_rewards": -2.0285701014540214,
    "random_rewards": -0.8854499419673367,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0271830735431635,
    "equal_rewards": -2.002073962278515,
    "random_rewards": -1.8805216443541029,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9927676527290505,
    "equal_rewards": -2.0409927661894063,
    "random_rewards": -0.5976974501391246,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0059373821992215,
    "equal_rewards": -2.0479741456933818,
    "random_rewards": -1.9820512759717404,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0552732264530698,
    "equal_rewards": -2.0221509239975046,
    "random_rewards": -2.184287432591921,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.014117348853974,
    "equal_rewards": -2.030070361677703,
    "random_rewards": -2.540081603020383,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013371447392613,
    "equal_rewards": -2.0047635664174024,
    "random_rewards": -0.8722142124573935,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.98669829462593,
    "equal_rewards": -2.046515512437428,
    "random_rewards": -0.8984702249725294,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0115487894643413,
    "equal_rewards": -2.0473331226449876,
    "random_rewards": -1.9548046156723313,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0350668764531115,
    "equal_rewards": -2.0014573015420822,
    "random_rewards": -2.4944404140169403,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9977228661821873,
    "equal_rewards": -2.0620588252713072,
    "random_rewards": -2.7219356473769514,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.04559465664225,
    "equal_rewards": -2.0152000382456814,
    "random_rewards": -2.654165904030897,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0163746061820347,
    "equal_rewards": -2.0018404879435963,
    "random_rewards": -1.6168221163502188,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9903037134526966,
    "equal_rewards": -2.0345986463505965,
    "random_rewards": -2.0769116038858657,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.993630273292995,
    "equal_rewards": -2.021126116494787,
    "random_rewards": -2.3797163351842454,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0038885655941225,
    "equal_rewards": -1.987050968306891,
    "random_rewards": -0.9994792398332346,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000363556581382,
    "equal_rewards": -2.0305972447707696,
    "random_rewards": -0.4457408586082176,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0247995833748362,
    "equal_rewards": -2.0086866550166538,
    "random_rewards": -1.4872158966812563,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.037609986617495,
    "equal_rewards": -2.0051606068971264,
    "random_rewards": -0.7387278374412513,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.984488034349005,
    "equal_rewards": -2.0256345585998625,
    "random_rewards": -2.2199966420054613,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9834864041497962,
    "equal_rewards": -1.9868631675547221,
    "random_rewards": -2.058096607107838,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.01346340731156,
    "equal_rewards": -1.976865183494993,
    "random_rewards": -2.1948389027023243,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9609996444761848,
    "equal_rewards": -2.019822540354233,
    "random_rewards": -2.0833302538490344,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0386807773713436,
    "equal_rewards": -2.013547762419804,
    "random_rewards": -2.0450248469309074,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.995740279862077,
    "equal_rewards": -2.028964305927161,
    "random_rewards": -1.4713802850704565,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.979560375811345,
    "equal_rewards": -2.022067252900936,
    "random_rewards": -0.592223614588661,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0166714113537676,
    "equal_rewards": -2.005659741292476,
    "random_rewards": -2.0655931790157016,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0258409698917683,
    "equal_rewards": -2.0171955443812353,
    "random_rewards": -2.3553176597894705,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9924271090955514,
    "equal_rewards": -2.052600181414954,
    "random_rewards": -1.2095477136405517,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.053390751938084,
    "equal_rewards": -2.0110766340681283,
    "random_rewards": -2.3576684365287566,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0155270977450717,
    "equal_rewards": -2.0329893428059433,
    "random_rewards": -1.9491743609876173,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0244840491124427,
    "equal_rewards": -1.9987933516500476,
    "random_rewards": -1.302751366520834,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9909634550131852,
    "equal_rewards": -2.0132866554512376,
    "random_rewards": -2.0634337313981908,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9630175658256712,
    "equal_rewards": -2.025171214936876,
    "random_rewards": -2.186368761017123,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0490354046992816,
    "equal_rewards": -2.0115918404433177,
    "random_rewards": -1.459611598852341,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9937430538722127,
    "equal_rewards": -2.0094129612025666,
    "random_rewards": -2.0735067785228134,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011212828047088,
    "equal_rewards": -1.9891804246675022,
    "random_rewards": -1.2756224589734582,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0075136628295773,
    "equal_rewards": -2.031956455902761,
    "random_rewards": -1.9486992966587708,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9719575382924963,
    "equal_rewards": -1.9920830280065545,
    "random_rewards": -2.908101791108986,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9631615279782966,
    "equal_rewards": -2.010056851554092,
    "random_rewards": -1.3267856248918146,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0125933198204202,
    "equal_rewards": -2.0457577306667565,
    "random_rewards": -1.1896350472999098,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016848016727851,
    "equal_rewards": -1.9960817690171242,
    "random_rewards": -1.7626247371609145,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.029722677049636,
    "equal_rewards": -1.986075764691697,
    "random_rewards": -2.0195666190692467,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9705824721928966,
    "equal_rewards": -2.0068413363436908,
    "random_rewards": -2.782625877184338,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0008278483132997,
    "equal_rewards": -1.9816129361867472,
    "random_rewards": -1.029241675674807,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9696041481168693,
    "equal_rewards": -2.013983254778873,
    "random_rewards": -1.6334992929354781,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0025623087627995,
    "equal_rewards": -1.9930036349743014,
    "random_rewards": -2.7562269947052163,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.001533650147436,
    "equal_rewards": -2.0241569797200754,
    "random_rewards": -2.064307304758248,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9856866128526507,
    "equal_rewards": -2.04081700474835,
    "random_rewards": -1.1852473168851527,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021691102822951,
    "equal_rewards": -2.008858097432692,
    "random_rewards": -1.9455648871432172,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9823388828563218,
    "equal_rewards": -2.0340967905713163,
    "random_rewards": -2.3648686438227684,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0164966786453618,
    "equal_rewards": -2.0022625574698623,
    "random_rewards": -2.2056119391647258,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0187472195954097,
    "equal_rewards": -2.002763770792562,
    "random_rewards": -1.4525561166710996,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9937637860000779,
    "equal_rewards": -2.0347888717931726,
    "random_rewards": -2.23368320559261,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.039944475687622,
    "equal_rewards": -2.0067248179567065,
    "random_rewards": -2.0802901012442554,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0268600187682746,
    "equal_rewards": -1.9917906833585102,
    "random_rewards": -1.904075197407826,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.00315856805091,
    "equal_rewards": -2.0372034515079163,
    "random_rewards": -1.7957450290634198,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.999596273548854,
    "equal_rewards": -2.049175646176856,
    "random_rewards": -1.8302510170014263,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0015948658334675,
    "equal_rewards": -2.01742789773893,
    "random_rewards": -2.6520889400660534,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.024630511583859,
    "equal_rewards": -2.0088185242822654,
    "random_rewards": -1.9189157919272688,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0276005375801147,
    "equal_rewards": -2.026248648551341,
    "random_rewards": -2.1047802139378327,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004415639505269,
    "equal_rewards": -2.0632856411917277,
    "random_rewards": -1.5040143955979992,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.015298705568013,
    "equal_rewards": -2.0273259452623282,
    "random_rewards": -1.9085152450356841,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.027101752211941,
    "equal_rewards": -1.9950674672704398,
    "random_rewards": -1.889031444233943,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0270298391794648,
    "equal_rewards": -2.0498738638981298,
    "random_rewards": -1.4697101985569505,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0449235249422935,
    "equal_rewards": -2.03268257482927,
    "random_rewards": -1.6561481066724277,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016582720712478,
    "equal_rewards": -2.025921135339768,
    "random_rewards": -0.7269983923317391,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9730911467437018,
    "equal_rewards": -2.0187655749735662,
    "random_rewards": -2.228112371293241,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0103706113479656,
    "equal_rewards": -2.0353039501584194,
    "random_rewards": -2.8142846368840746,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.050825511416398,
    "equal_rewards": -2.035057573474481,
    "random_rewards": -1.776806444786033,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004259268138365,
    "equal_rewards": -2.03763904805775,
    "random_rewards": -2.242881562428268,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0063443049366985,
    "equal_rewards": -2.0275454812594087,
    "random_rewards": -1.7999594966381784,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0255622863906284,
    "equal_rewards": -2.029403241446667,
    "random_rewards": -2.3911528668017383,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9833194148242024,
    "equal_rewards": -2.0393503663536365,
    "random_rewards": -2.52329465377695,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.051820474833528,
    "equal_rewards": -2.0159845791203033,
    "random_rewards": -1.609744215859715,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0118386524846232,
    "equal_rewards": -2.0361182655676275,
    "random_rewards": -2.0631399779714643,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0440704652779074,
    "equal_rewards": -2.013050341062802,
    "random_rewards": -1.3419483794794105,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.032115284705532,
    "equal_rewards": -2.060799967362441,
    "random_rewards": -2.134569618851315,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0128217190906192,
    "equal_rewards": -2.0293562599593615,
    "random_rewards": -1.7573018560084905,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0037883466239936,
    "equal_rewards": -2.02158689937515,
    "random_rewards": -1.9161653338008542,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0420756506322166,
    "equal_rewards": -2.0637558195738457,
    "random_rewards": -2.569958562313042,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0119558735772554,
    "equal_rewards": -2.0551252129486173,
    "random_rewards": -1.4821964601718394,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0066539164594746,
    "equal_rewards": -2.024336579831881,
    "random_rewards": -1.3567222477403107,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.026535966560168,
    "equal_rewards": -2.047119748192601,
    "random_rewards": -0.7342827077093577,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0299960001015656,
    "equal_rewards": -2.0254981713529223,
    "random_rewards": -1.4486219766696775,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0033516129926054,
    "equal_rewards": -2.0088158778739005,
    "random_rewards": -1.4470820409508534,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.032599632022637,
    "equal_rewards": -2.016031698745367,
    "random_rewards": -2.08192106987285,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0313654660606533,
    "equal_rewards": -2.0599671736481153,
    "random_rewards": -1.3422257222512366,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0157770083069373,
    "equal_rewards": -2.0275494313426625,
    "random_rewards": -2.9611611831191365,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9936474473040762,
    "equal_rewards": -2.0042824706192546,
    "random_rewards": -1.1806530797899693,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9964898620040876,
    "equal_rewards": -2.0217051442862806,
    "random_rewards": -0.8759143765684634,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.055987569514838,
    "equal_rewards": -2.0216141093913773,
    "random_rewards": -0.5867468522825292,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9895969422891029,
    "equal_rewards": -2.0431012195192144,
    "random_rewards": -2.1058942076141705,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9899633522265647,
    "equal_rewards": -2.0379255017830733,
    "random_rewards": -1.0525965251063225,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0407288011054963,
    "equal_rewards": -2.007911974166595,
    "random_rewards": -1.915410715886588,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9977840533141684,
    "equal_rewards": -2.017545830038629,
    "random_rewards": -1.8074916779841932,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0226797192989303,
    "equal_rewards": -2.0112271546079854,
    "random_rewards": -1.9013022459668067,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.986213962212583,
    "equal_rewards": -1.9888139644594918,
    "random_rewards": -1.8847974106215268,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9588498392974798,
    "equal_rewards": -1.9948768587239993,
    "random_rewards": -1.7448395176038352,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.993832191144468,
    "equal_rewards": -2.017210078138021,
    "random_rewards": -1.59483705961487,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9388457543542543,
    "equal_rewards": -1.9827702870962904,
    "random_rewards": -1.1518600775429375,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9729257775519393,
    "equal_rewards": -1.9606128590069636,
    "random_rewards": -1.8666383497328303,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0133757602100997,
    "equal_rewards": -2.039848922390261,
    "random_rewards": -1.1865777242357827,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.056468752161605,
    "equal_rewards": -2.018821356166721,
    "random_rewards": -1.7683995715825835,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.003014085883787,
    "equal_rewards": -2.042454078146741,
    "random_rewards": -2.1168673376191633,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.987202027047129,
    "equal_rewards": -2.0347649305654105,
    "random_rewards": -1.3617761605086005,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9910880943544587,
    "equal_rewards": -1.9706397239835933,
    "random_rewards": -2.5748501324073634,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9983110783777684,
    "equal_rewards": -1.9889305360106087,
    "random_rewards": -1.0237423808406636,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0159967091710858,
    "equal_rewards": -2.0392022634405738,
    "random_rewards": -0.4476297651454918,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9981966358956718,
    "equal_rewards": -2.0349432728309678,
    "random_rewards": -2.8210918116753687,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.963919645186269,
    "equal_rewards": -2.027664419161751,
    "random_rewards": -1.5849625017212656,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.018185011573604,
    "equal_rewards": -2.004281844699269,
    "random_rewards": -1.925084732758525,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013950073985849,
    "equal_rewards": -2.04117687247362,
    "random_rewards": -1.317974657826512,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.041088726889148,
    "equal_rewards": -2.024247958014326,
    "random_rewards": -0.7285952186178875,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0287367789478,
    "equal_rewards": -2.0237066059587456,
    "random_rewards": -1.0344031223526768,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0064337556181644,
    "equal_rewards": -2.022242291651387,
    "random_rewards": -1.493516303193732,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0099730577943182,
    "equal_rewards": -1.9842795570092757,
    "random_rewards": -0.871147122589438,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9598990871388988,
    "equal_rewards": -2.0292297108387936,
    "random_rewards": -1.0494794425940845,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.025649690962782,
    "equal_rewards": -2.020290137743855,
    "random_rewards": -1.7333396106186019,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021368003700919,
    "equal_rewards": -1.995727174392323,
    "random_rewards": -2.048894965590461,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9529971713725294,
    "equal_rewards": -2.014898019321995,
    "random_rewards": -1.6321562528818039,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.986124711740298,
    "equal_rewards": -1.9735446734702842,
    "random_rewards": -1.5748603277839308,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9647391855259921,
    "equal_rewards": -2.004671759252978,
    "random_rewards": -2.0634611863519163,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.995455780531564,
    "equal_rewards": -1.981366673999264,
    "random_rewards": -1.448155455700767,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9837552767894506,
    "equal_rewards": -2.040667174975468,
    "random_rewards": -1.1960693296870617,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0044625229577724,
    "equal_rewards": -2.011250220712867,
    "random_rewards": -1.445862862932881,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.026585251506135,
    "equal_rewards": -1.9948891691387045,
    "random_rewards": -2.195304761453867,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0027727639107322,
    "equal_rewards": -2.0530629934280373,
    "random_rewards": -1.6437786221880164,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9735969841282301,
    "equal_rewards": -2.014798117870521,
    "random_rewards": -2.048356821786612,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9986507488333936,
    "equal_rewards": -1.9712973883269371,
    "random_rewards": -2.43790165867057,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.002119095670089,
    "equal_rewards": -2.031326680340042,
    "random_rewards": -2.2228640535975606,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.998474225035337,
    "equal_rewards": -2.019389557977957,
    "random_rewards": -1.346210425467619,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0059725871125016,
    "equal_rewards": -1.993327116311224,
    "random_rewards": -2.0335032101128556,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9934870734340793,
    "equal_rewards": -2.0235150458232587,
    "random_rewards": -1.2207973899078082,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.032268847670869,
    "equal_rewards": -2.0067852748920956,
    "random_rewards": -1.7617222328337707,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0014663137508566,
    "equal_rewards": -2.055865821117747,
    "random_rewards": -1.8120064245086214,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9740102892737672,
    "equal_rewards": -2.01261167170126,
    "random_rewards": -2.0764136721007094,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0048791155444325,
    "equal_rewards": -1.9843030365799137,
    "random_rewards": -2.0227077762404226,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0446985830477025,
    "equal_rewards": -2.0226512914935713,
    "random_rewards": -2.0580403154819704,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.999004132617991,
    "equal_rewards": -2.0684073065357103,
    "random_rewards": -1.3598431020428348,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0392574897775932,
    "equal_rewards": -2.0283098484560975,
    "random_rewards": -1.9075667798411438,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9997026982515336,
    "equal_rewards": -2.0574844851305194,
    "random_rewards": -1.6829482738510133,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0058382553019958,
    "equal_rewards": -2.039039683409766,
    "random_rewards": -1.7594236749421943,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0341156957238598,
    "equal_rewards": -1.9978375606059413,
    "random_rewards": -1.0292831540618794,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0138626275880567,
    "equal_rewards": -2.0325559952636563,
    "random_rewards": -1.9586573922587949,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004056074367581,
    "equal_rewards": -2.0341025593106106,
    "random_rewards": -1.7975820529521545,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004110078758068,
    "equal_rewards": -2.012041102679989,
    "random_rewards": -2.2372879471555356,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0084153402817337,
    "equal_rewards": -1.9911554257336883,
    "random_rewards": -1.3040304569637073,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0278538143808733,
    "equal_rewards": -2.001833070705304,
    "random_rewards": -1.6304072778120005,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.996147366302534,
    "equal_rewards": -2.052461311394835,
    "random_rewards": -1.3469108698450003,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9778670224933328,
    "equal_rewards": -2.023245130901305,
    "random_rewards": -1.6289254270710574,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.006157031224581,
    "equal_rewards": -1.9683307396317964,
    "random_rewards": -0.7126856642703066,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.98561075414358,
    "equal_rewards": -2.010728760509326,
    "random_rewards": -1.635771621326355,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0074421816255836,
    "equal_rewards": -2.000518992430928,
    "random_rewards": -1.765174392862932,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9658671444065532,
    "equal_rewards": -2.0202877425775143,
    "random_rewards": -0.5986766249659914,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0427743836105483,
    "equal_rewards": -2.0299367066913083,
    "random_rewards": -2.374170945912567,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0285126762297088,
    "equal_rewards": -2.0091844959563305,
    "random_rewards": -2.197419490871675,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.020057125802783,
    "equal_rewards": -2.039312253302106,
    "random_rewards": -1.8963792785695897,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0051101209608295,
    "equal_rewards": -2.046060158878306,
    "random_rewards": -1.9290386304714233,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.005875375047861,
    "equal_rewards": -2.023171169340771,
    "random_rewards": -1.009986162281004,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.023119513161005,
    "equal_rewards": -2.0485656756334105,
    "random_rewards": -1.4984371790529012,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0012840264878164,
    "equal_rewards": -2.0143555762788234,
    "random_rewards": -2.061991310217662,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.965090991832179,
    "equal_rewards": -2.0037417565035147,
    "random_rewards": -1.426728592393958,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0027959450484007,
    "equal_rewards": -2.023404592993484,
    "random_rewards": -1.8048395410514941,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9943874935252544,
    "equal_rewards": -2.0294078417426675,
    "random_rewards": -1.919804604745132,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016841779526672,
    "equal_rewards": -1.988150428441538,
    "random_rewards": -2.3521022496342834,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9965150281132922,
    "equal_rewards": -2.021300487489739,
    "random_rewards": -1.773577063505891,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9776191039916824,
    "equal_rewards": -2.0216468590423284,
    "random_rewards": -1.010994949873902,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.97854401113335,
    "equal_rewards": -1.9657384866931702,
    "random_rewards": -1.4613032031744257,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9235289462242209,
    "equal_rewards": -1.9353338486719438,
    "random_rewards": -1.9840262686893402,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.8910858472127043,
    "equal_rewards": -1.9542641917955408,
    "random_rewards": -0.85796964517853,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9715648234084333,
    "equal_rewards": -1.955583694511751,
    "random_rewards": -1.1540312675070221,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.956918470833024,
    "equal_rewards": -1.96910905944252,
    "random_rewards": -2.3411394704808197,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9653682919901758,
    "equal_rewards": -1.9629088577834453,
    "random_rewards": -1.7243059736296122,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9863826999119112,
    "equal_rewards": -2.034876043913621,
    "random_rewards": -2.282670490504862,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.994923482381468,
    "equal_rewards": -2.024504193482479,
    "random_rewards": -1.6600139849154003,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9999010699191566,
    "equal_rewards": -2.0491860420449926,
    "random_rewards": -1.6785389471327838,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0281568636321707,
    "equal_rewards": -2.022669317132414,
    "random_rewards": -1.3397027887540416,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.012753243771716,
    "equal_rewards": -2.0385638364985703,
    "random_rewards": -2.5430091985113346,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9779463594460633,
    "equal_rewards": -2.0368265789324456,
    "random_rewards": -1.3326454094011941,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.03729083056521,
    "equal_rewards": -1.99531171042063,
    "random_rewards": -1.4484820084684553,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0098282802272696,
    "equal_rewards": -2.0193924035484674,
    "random_rewards": -1.777808000798219,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0216282765447673,
    "equal_rewards": -1.9799198152825463,
    "random_rewards": -0.8692330896362397,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9640973541152333,
    "equal_rewards": -1.9878109698484603,
    "random_rewards": -2.0439469319127026,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9623242725738894,
    "equal_rewards": -1.9880160527636002,
    "random_rewards": -2.618362606078888,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0086725135924564,
    "equal_rewards": -2.0000852955552118,
    "random_rewards": -1.7815786001949983,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.99718845837005,
    "equal_rewards": -2.0241178168939347,
    "random_rewards": -1.9422480229909638,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9996388407555223,
    "equal_rewards": -2.0216229722519468,
    "random_rewards": -2.374834168471032,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.984454486763641,
    "equal_rewards": -2.0246135915585155,
    "random_rewards": -1.9311090712376011,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9640175011625733,
    "equal_rewards": -2.0291881206747755,
    "random_rewards": -2.399247943222953,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.023086554252175,
    "equal_rewards": -2.018404853456636,
    "random_rewards": -2.2399252338126985,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0179899642362598,
    "equal_rewards": -2.005443814324405,
    "random_rewards": -2.3535244627374787,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9685007460622868,
    "equal_rewards": -1.9762822522398462,
    "random_rewards": -1.7204644075930582,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.954561842409586,
    "equal_rewards": -2.008611373067539,
    "random_rewards": -1.6009104061673547,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.029081280874893,
    "equal_rewards": -2.00297545483304,
    "random_rewards": -1.7774307751787468,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.970983138656218,
    "equal_rewards": -1.9831129579930973,
    "random_rewards": -2.307742036424643,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9691530868366942,
    "equal_rewards": -2.0000687276509588,
    "random_rewards": -1.7698425808253946,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0324629716642306,
    "equal_rewards": -2.0048592702770938,
    "random_rewards": -1.7360774537592714,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9825849285552792,
    "equal_rewards": -2.024669841316796,
    "random_rewards": -1.198913223422553,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9690541329985791,
    "equal_rewards": -2.001855733300707,
    "random_rewards": -1.6288592875418224,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.002212920070148,
    "equal_rewards": -2.022168746643881,
    "random_rewards": -2.4932891926010052,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0376096683455556,
    "equal_rewards": -2.0642373945925745,
    "random_rewards": -1.9481310743748435,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0040269793800176,
    "equal_rewards": -2.05633791814992,
    "random_rewards": -1.4783103910514743,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.019124046982744,
    "equal_rewards": -2.0026862460868555,
    "random_rewards": -1.4805852979357697,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9706215013875898,
    "equal_rewards": -1.988736937887107,
    "random_rewards": -2.59834049210833,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9674676540426912,
    "equal_rewards": -1.9660104215947638,
    "random_rewards": -1.0118467348817148,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021900434358588,
    "equal_rewards": -2.0467525253553616,
    "random_rewards": -2.1029282245035636,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.020338597510696,
    "equal_rewards": -2.0119666756629164,
    "random_rewards": -1.5918674937083206,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9493753387403219,
    "equal_rewards": -2.0266627406675113,
    "random_rewards": -2.539764752426274,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.015596131431094,
    "equal_rewards": -1.997738012415856,
    "random_rewards": -1.6009964265636736,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0090122007567133,
    "equal_rewards": -1.9872987446270218,
    "random_rewards": -2.763985683429172,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9344812124706519,
    "equal_rewards": -1.9544459989897836,
    "random_rewards": -1.8741815126610761,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9474316005577779,
    "equal_rewards": -1.9789260365633488,
    "random_rewards": -2.0190382380769316,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013399346714915,
    "equal_rewards": -1.9846187146199785,
    "random_rewards": -0.5758651847025451,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.983769239165127,
    "equal_rewards": -2.0239475899306503,
    "random_rewards": -2.5331932981638428,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9475136269152677,
    "equal_rewards": -1.990069625082468,
    "random_rewards": -1.2959313812223547,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9782225827218132,
    "equal_rewards": -1.94839927272404,
    "random_rewards": -1.708284741567599,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9618529441004458,
    "equal_rewards": -1.942452278670835,
    "random_rewards": -1.4161694432767606,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.968516903558884,
    "equal_rewards": -1.9977620014367643,
    "random_rewards": -1.3299653504305315,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.980883636301773,
    "equal_rewards": -1.9944367720488358,
    "random_rewards": -1.9307268305308567,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9866539279898832,
    "equal_rewards": -1.9793991686504389,
    "random_rewards": -1.6224123970740119,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9385686373009505,
    "equal_rewards": -1.987131971273846,
    "random_rewards": -1.4898316295318368,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9547432578867627,
    "equal_rewards": -2.014284138073682,
    "random_rewards": -1.929902342011263,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0401888995301505,
    "equal_rewards": -2.018630068369279,
    "random_rewards": -1.7685349145303497,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9967401003744385,
    "equal_rewards": -2.036649550047749,
    "random_rewards": -1.014515596860083,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0045990827922333,
    "equal_rewards": -2.0207493907066874,
    "random_rewards": -1.9229763722885904,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9743540818350165,
    "equal_rewards": -2.028186330258167,
    "random_rewards": -2.0999844605364153,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0377244381244783,
    "equal_rewards": -1.9944080909549813,
    "random_rewards": -1.0207137027361324,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9898125699658973,
    "equal_rewards": -2.0453753745465884,
    "random_rewards": -2.3709050292190925,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0347337821503952,
    "equal_rewards": -2.0666757248927348,
    "random_rewards": -1.623841091886327,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.03633113891842,
    "equal_rewards": -2.0224172139208205,
    "random_rewards": -2.811820129047584,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0130967191459934,
    "equal_rewards": -1.9887259706873808,
    "random_rewards": -2.186039879020222,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0021213909404034,
    "equal_rewards": -1.9723759363726525,
    "random_rewards": -1.0213447091243504,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9714363628284308,
    "equal_rewards": -2.0202106536248583,
    "random_rewards": -2.9493584902044687,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0360431216857373,
    "equal_rewards": -2.0132253015635952,
    "random_rewards": -2.3860020380995968,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9994854510736377,
    "equal_rewards": -2.029146345653397,
    "random_rewards": -2.068664289231818,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9821621290063927,
    "equal_rewards": -2.04378278832851,
    "random_rewards": -1.0625368657334293,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0204656905164264,
    "equal_rewards": -2.012164128858452,
    "random_rewards": -2.50383384788339,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9686945872634662,
    "equal_rewards": -2.0338818028675734,
    "random_rewards": -2.376411052051667,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9939806736719006,
    "equal_rewards": -2.0351376440515683,
    "random_rewards": -2.255581588984164,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9970406047911533,
    "equal_rewards": -2.0220595943184234,
    "random_rewards": -2.0482968104007546,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.020251226401135,
    "equal_rewards": -1.999025856955746,
    "random_rewards": -1.1709137058900811,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.997345937881143,
    "equal_rewards": -2.024099642764762,
    "random_rewards": -0.9040319816304481,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0338585604261796,
    "equal_rewards": -2.0201658622858143,
    "random_rewards": -1.1925323481600743,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0060784124813256,
    "equal_rewards": -2.023704186568855,
    "random_rewards": -2.2570173806690335,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0161705718467875,
    "equal_rewards": -2.0003338016329772,
    "random_rewards": -1.9280807915184373,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0437019512781784,
    "equal_rewards": -2.0089105237282183,
    "random_rewards": -2.5163506278385053,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9800890929464132,
    "equal_rewards": -2.010377045678265,
    "random_rewards": -1.1787062208970194,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9836762888920534,
    "equal_rewards": -2.024989582720088,
    "random_rewards": -2.3652472120094457,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9898289548281447,
    "equal_rewards": -2.01381135362696,
    "random_rewards": -2.0629196512945205,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9598189789215152,
    "equal_rewards": -2.01445311799565,
    "random_rewards": -2.194464674256392,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0404392263788975,
    "equal_rewards": -2.0023820688629606,
    "random_rewards": -2.482022891241615,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0023325159574883,
    "equal_rewards": -2.0512422200670657,
    "random_rewards": -3.0096219785592524,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9940919176339205,
    "equal_rewards": -2.0268642568074786,
    "random_rewards": -1.1870758043055742,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013747324737137,
    "equal_rewards": -1.9916022201230241,
    "random_rewards": -1.8787165782786226,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9978695763019654,
    "equal_rewards": -2.023866775687734,
    "random_rewards": -1.7600452080485345,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0033522338666043,
    "equal_rewards": -2.021987959440163,
    "random_rewards": -1.4580620076825679,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.003369302042205,
    "equal_rewards": -2.0285544777344238,
    "random_rewards": -1.3447264263725858,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9290564232988237,
    "equal_rewards": -1.9762046668572586,
    "random_rewards": -1.303262246536872,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9851686997037614,
    "equal_rewards": -1.9734319947938332,
    "random_rewards": -1.8626158469173588,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0157028518263007,
    "equal_rewards": -1.990818616598934,
    "random_rewards": -1.6375923536005978,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.997735501566289,
    "equal_rewards": -2.021916708980092,
    "random_rewards": -0.5910692572035011,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9981857740833218,
    "equal_rewards": -2.0364117898416065,
    "random_rewards": -2.0568738150318127,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0281867143149386,
    "equal_rewards": -2.0475333212159468,
    "random_rewards": -2.398588146329988,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0134401507162942,
    "equal_rewards": -2.0426095583506325,
    "random_rewards": -2.103695601504547,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9993819860173836,
    "equal_rewards": -2.055334024565894,
    "random_rewards": -1.7961548022548701,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9991322407648537,
    "equal_rewards": -2.001948521777024,
    "random_rewards": -2.0426169552198625,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0044252729927092,
    "equal_rewards": -1.9914065113428054,
    "random_rewards": -2.6193905989556576,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0364127527514357,
    "equal_rewards": -2.015913428353829,
    "random_rewards": -1.8917387415596951,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.965304253985556,
    "equal_rewards": -2.0336352020288366,
    "random_rewards": -1.6746968702479486,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0212966989756795,
    "equal_rewards": -2.008353211648921,
    "random_rewards": -1.317979813459995,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0355982134457227,
    "equal_rewards": -2.000770574870548,
    "random_rewards": -1.4689426759715745,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9693600449117694,
    "equal_rewards": -2.0221657400955526,
    "random_rewards": -2.0622378654920492,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9913883956230638,
    "equal_rewards": -2.0456742684146176,
    "random_rewards": -2.1049588110231503,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9932677609080334,
    "equal_rewards": -2.0072183493549156,
    "random_rewards": -2.790044860215551,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9927235284218805,
    "equal_rewards": -1.9962093436017003,
    "random_rewards": -1.9069808015494396,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0326344849481286,
    "equal_rewards": -2.0056925879853162,
    "random_rewards": -1.9263801111556174,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.012041587247359,
    "equal_rewards": -2.042533912902309,
    "random_rewards": -1.1887322497215937,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.022513490019441,
    "equal_rewards": -2.010237408226118,
    "random_rewards": -2.0668585788947094,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.008742702487314,
    "equal_rewards": -1.994794311392325,
    "random_rewards": -1.1568187322054881,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9954304283142432,
    "equal_rewards": -2.0495764191461014,
    "random_rewards": -1.1990207644764856,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9989810724868389,
    "equal_rewards": -2.034037602142244,
    "random_rewards": -2.188761915840624,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9880949948831579,
    "equal_rewards": -2.012655741791207,
    "random_rewards": -2.2222585090598734,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9794682322911097,
    "equal_rewards": -2.0221598029360175,
    "random_rewards": -1.7884316697310763,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0051612491704223,
    "equal_rewards": -2.0219298151311342,
    "random_rewards": -1.1673931886091153,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9910832725936918,
    "equal_rewards": -2.0500396379561154,
    "random_rewards": -0.764376187468899,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0416441308635966,
    "equal_rewards": -2.007081686517073,
    "random_rewards": -1.4644897707793074,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9929074916601857,
    "equal_rewards": -2.025850759485007,
    "random_rewards": -0.8945457498262404,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.00564611862696,
    "equal_rewards": -2.027091691510172,
    "random_rewards": -1.4787931206060914,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.028609882737741,
    "equal_rewards": -2.0140516168321816,
    "random_rewards": -1.9059515554259114,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9696277949110228,
    "equal_rewards": -2.019410473016481,
    "random_rewards": -1.4691175599412185,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0041250460689044,
    "equal_rewards": -2.026003220375608,
    "random_rewards": -1.9325573249666486,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.01073050632105,
    "equal_rewards": -2.034435709863711,
    "random_rewards": -2.390850619097962,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9983592356676398,
    "equal_rewards": -2.0231511870289896,
    "random_rewards": -1.489284468087812,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9739365168106047,
    "equal_rewards": -2.0401751817247336,
    "random_rewards": -1.9361486235964387,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.06047767590218,
    "equal_rewards": -2.023206050796894,
    "random_rewards": -2.3848728403295723,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0386503761216868,
    "equal_rewards": -2.0218088010548203,
    "random_rewards": -1.0429147710258668,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9924290102052926,
    "equal_rewards": -2.04627336061672,
    "random_rewards": -1.3847280274916658,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0035932424506346,
    "equal_rewards": -2.0286159079815977,
    "random_rewards": -2.5435434984010206,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.012886951791204,
    "equal_rewards": -1.997071877200093,
    "random_rewards": -1.6206526141046962,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9940500076341607,
    "equal_rewards": -2.042255303757294,
    "random_rewards": -1.3606883049920129,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0151011946238477,
    "equal_rewards": -2.0311056043055933,
    "random_rewards": -0.7503179412412448,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0202035524313264,
    "equal_rewards": -2.0110713885608176,
    "random_rewards": -1.903263554402053,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9990503418881163,
    "equal_rewards": -2.0532763983481512,
    "random_rewards": -2.0844363531486496,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.041302813834002,
    "equal_rewards": -2.0256915102271162,
    "random_rewards": -1.9074355960816216,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.039514486084151,
    "equal_rewards": -2.0645364694586044,
    "random_rewards": -1.3662054100929075,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0220626730557365,
    "equal_rewards": -2.0240445831177123,
    "random_rewards": -1.9538453012674957,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9752110343182643,
    "equal_rewards": -2.009686054774068,
    "random_rewards": -2.1720919623185826,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013118654389243,
    "equal_rewards": -2.038020929791,
    "random_rewards": -2.6993259268822207,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007512416802972,
    "equal_rewards": -2.02807233232161,
    "random_rewards": -1.6379968051187292,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000738630451584,
    "equal_rewards": -2.0488606037329107,
    "random_rewards": -1.6266965248093355,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0431686393232775,
    "equal_rewards": -2.018827627110687,
    "random_rewards": -1.7805636336440085,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0296824577510564,
    "equal_rewards": -2.0133517958653115,
    "random_rewards": -1.7714346174365319,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0239957158540394,
    "equal_rewards": -2.0506663790953636,
    "random_rewards": -2.5348396217157854,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0152284257304283,
    "equal_rewards": -2.0405528134675786,
    "random_rewards": -1.7999358230601674,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011049370984278,
    "equal_rewards": -2.0277992179105833,
    "random_rewards": -1.1792018491396883,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016791051453032,
    "equal_rewards": -2.0376504850419885,
    "random_rewards": -1.6387371470184904,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.068807980164949,
    "equal_rewards": -2.04498629369818,
    "random_rewards": -0.7575517805057305,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0069978615754356,
    "equal_rewards": -2.0584089620783805,
    "random_rewards": -2.282729130041276,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0132780542749567,
    "equal_rewards": -2.0344911420189633,
    "random_rewards": -2.3742207367370516,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.032138266703847,
    "equal_rewards": -2.019111010357776,
    "random_rewards": -1.6618522019485016,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.003532249958667,
    "equal_rewards": -2.067261242858988,
    "random_rewards": -1.5048565554797118,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.030166076356644,
    "equal_rewards": -2.0338641334090033,
    "random_rewards": -1.3119808263273287,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9784804122259851,
    "equal_rewards": -2.030762627904493,
    "random_rewards": -2.088791878897066,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0198475806038823,
    "equal_rewards": -2.0088637092527373,
    "random_rewards": -2.6458204951133615,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9930181040939343,
    "equal_rewards": -2.053111899731589,
    "random_rewards": -1.686769477110607,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0368488535912164,
    "equal_rewards": -2.022848623942448,
    "random_rewards": -2.810677285182868,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.045457787244107,
    "equal_rewards": -2.0209999717779454,
    "random_rewards": -1.4889575093622391,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.028951131009907,
    "equal_rewards": -2.010101067777337,
    "random_rewards": -2.344256220850712,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.039449546180544,
    "equal_rewards": -2.018832650099573,
    "random_rewards": -1.9120314774819023,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9897766297600392,
    "equal_rewards": -2.0387291347787793,
    "random_rewards": -2.6839731285654893,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.989207616117388,
    "equal_rewards": -2.0560290424126633,
    "random_rewards": -1.1966378925313073,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016748660798865,
    "equal_rewards": -2.001084306913436,
    "random_rewards": -2.333878067730831,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9763273292550034,
    "equal_rewards": -2.0395015188565866,
    "random_rewards": -1.3642689531774896,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0279010897201375,
    "equal_rewards": -2.0182954055183204,
    "random_rewards": -2.0733278995161712,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.027260290714862,
    "equal_rewards": -1.992086648916083,
    "random_rewards": -1.5976810675974864,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9810536196934656,
    "equal_rewards": -2.0452252799146673,
    "random_rewards": -1.6008969973301237,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.032418076102325,
    "equal_rewards": -2.024654936794539,
    "random_rewards": -2.9679658915217235,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9948663259199282,
    "equal_rewards": -2.046728020015636,
    "random_rewards": -2.208684964240707,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016283296181658,
    "equal_rewards": -1.9979700464433963,
    "random_rewards": -2.0669679859827266,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0132130608711334,
    "equal_rewards": -1.9757815829413672,
    "random_rewards": -2.021365774062306,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9773758945810136,
    "equal_rewards": -2.0315695848054096,
    "random_rewards": -1.026401502338064,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0159258146916517,
    "equal_rewards": -2.0048466629556447,
    "random_rewards": -1.6307761179802467,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0150611560237506,
    "equal_rewards": -1.9738333949332731,
    "random_rewards": -1.0336366546556541,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.00390618726748,
    "equal_rewards": -2.0567016915442187,
    "random_rewards": -1.2136335058577903,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9991284070260158,
    "equal_rewards": -2.040040260652121,
    "random_rewards": -2.2172616032401624,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9926960753456235,
    "equal_rewards": -2.0219145498692934,
    "random_rewards": -2.344402691480386,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9993389851187682,
    "equal_rewards": -2.0379351483162966,
    "random_rewards": -1.9434130126302906,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.019772004420335,
    "equal_rewards": -2.0553481814365897,
    "random_rewards": -1.044779067226865,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0373099818671823,
    "equal_rewards": -2.0080178550984633,
    "random_rewards": -1.630851466307817,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.035444994547206,
    "equal_rewards": -1.9963495502420399,
    "random_rewards": -1.3080920052488698,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.004578163902981,
    "equal_rewards": -2.0303953507706805,
    "random_rewards": -2.500738522209918,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9994555682440236,
    "equal_rewards": -2.020942472911802,
    "random_rewards": -0.8660475149012448,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0302688073388855,
    "equal_rewards": -2.0202219454950816,
    "random_rewards": -1.9468870021937046,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9909066590569502,
    "equal_rewards": -2.047045655551653,
    "random_rewards": -1.3425918662590377,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.013679728485951,
    "equal_rewards": -2.0435671168538687,
    "random_rewards": -2.2362703432908426,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.006061854390644,
    "equal_rewards": -2.0597106242878986,
    "random_rewards": -0.9111393429701731,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0025894875394084,
    "equal_rewards": -2.0565544782854683,
    "random_rewards": -2.5287830469475105,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.043858416556887,
    "equal_rewards": -2.025359681988952,
    "random_rewards": -2.072355442847329,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9776746623034915,
    "equal_rewards": -2.0313604257884688,
    "random_rewards": -2.217635317548191,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0156871831069365,
    "equal_rewards": -2.0377759722958606,
    "random_rewards": -1.7869734230498693,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0189095865924394,
    "equal_rewards": -2.0358720212113117,
    "random_rewards": -0.9018711013661578,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0503713497173175,
    "equal_rewards": -2.019315068893557,
    "random_rewards": -2.0515352579038155,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.025878873261912,
    "equal_rewards": -2.0532239800648853,
    "random_rewards": -1.3750042041077237,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9931450511662048,
    "equal_rewards": -2.031208341170007,
    "random_rewards": -1.664308371751522,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0166088292710347,
    "equal_rewards": -1.9995072450929752,
    "random_rewards": -2.6216627487391118,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.04149731306156,
    "equal_rewards": -2.0113452946453445,
    "random_rewards": -2.513876666419152,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0011036414929007,
    "equal_rewards": -2.04999858520285,
    "random_rewards": -2.2886322647197868,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0317771922481374,
    "equal_rewards": -2.012640079244864,
    "random_rewards": -1.9489962602264075,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.981801728183091,
    "equal_rewards": -2.022194662344986,
    "random_rewards": -3.1072747250666852,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.977187488592643,
    "equal_rewards": -2.0302054449433986,
    "random_rewards": -1.9613137318111589,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0243448660531422,
    "equal_rewards": -2.049320868448293,
    "random_rewards": -2.241002064658606,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.02173279984771,
    "equal_rewards": -2.0377076898348085,
    "random_rewards": -1.9618921671568659,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.995875792932538,
    "equal_rewards": -2.0461476584039078,
    "random_rewards": -1.7882385848820146,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.989867100820093,
    "equal_rewards": -2.043812061186632,
    "random_rewards": -2.0629148388404377,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.008458814944555,
    "equal_rewards": -2.0542795446215214,
    "random_rewards": -1.8254686488370115,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0184908422626937,
    "equal_rewards": -2.042459769178206,
    "random_rewards": -2.391464133641693,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9949079666710965,
    "equal_rewards": -2.0104481193062673,
    "random_rewards": -1.9291732589257347,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0091754945122853,
    "equal_rewards": -1.99861111545769,
    "random_rewards": -2.918090136677558,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0189483818309966,
    "equal_rewards": -2.0399549574679683,
    "random_rewards": -2.0741084706379307,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0262949474810696,
    "equal_rewards": -2.0512881747692173,
    "random_rewards": -1.6216967275654293,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9982937735864024,
    "equal_rewards": -2.0597029979892802,
    "random_rewards": -1.3543317200283482,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0424746471898816,
    "equal_rewards": -2.037633786329443,
    "random_rewards": -1.771358068017534,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.033302232988914,
    "equal_rewards": -2.0571358686195387,
    "random_rewards": -1.3587012465468682,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.040759612049767,
    "equal_rewards": -2.0357578503218643,
    "random_rewards": -1.9058665108668809,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0012415859714325,
    "equal_rewards": -2.0230691313893816,
    "random_rewards": -1.734257403210067,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9855308565317509,
    "equal_rewards": -2.01069521594493,
    "random_rewards": -2.3368968584784153,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9917673225478265,
    "equal_rewards": -2.046035070800023,
    "random_rewards": -2.5528853063177825,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.042017563933841,
    "equal_rewards": -2.0136165615494086,
    "random_rewards": -1.4967205896594402,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9968783192095576,
    "equal_rewards": -2.0166237584757583,
    "random_rewards": -1.4978181231397167,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9825211882311558,
    "equal_rewards": -2.035806849586724,
    "random_rewards": -2.2182334325146718,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.014990359528096,
    "equal_rewards": -2.0357793055600197,
    "random_rewards": -2.9742136049701178,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0294990822101466,
    "equal_rewards": -2.050787778514019,
    "random_rewards": -1.8006917079635287,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.036701107428139,
    "equal_rewards": -2.0217065291692853,
    "random_rewards": -1.4767427147844487,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.002921880329689,
    "equal_rewards": -2.028408494887555,
    "random_rewards": -1.4843285410331206,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9982659799766442,
    "equal_rewards": -2.050610676250795,
    "random_rewards": -2.098410124176081,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.023423800595757,
    "equal_rewards": -2.0570621178154695,
    "random_rewards": -2.3773065986646422,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0428041317596772,
    "equal_rewards": -2.0132259108202706,
    "random_rewards": -2.068275653881468,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9790898696514148,
    "equal_rewards": -2.0242894171471804,
    "random_rewards": -2.517342761076201,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.987288216543135,
    "equal_rewards": -2.044168899526835,
    "random_rewards": -0.890591959178162,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.012442884894111,
    "equal_rewards": -2.017735027552684,
    "random_rewards": -1.4419406728652218,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0304412734124853,
    "equal_rewards": -1.988256514233723,
    "random_rewards": -1.5854476275073124,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0013454718077983,
    "equal_rewards": -2.0553650805121952,
    "random_rewards": -2.4135552844690817,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.019301103144034,
    "equal_rewards": -2.0359499651115938,
    "random_rewards": -1.66373529777198,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.03030777262279,
    "equal_rewards": -2.0197957327103833,
    "random_rewards": -2.221168434768633,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.029568197499384,
    "equal_rewards": -2.0552066570337404,
    "random_rewards": -2.3764826799526273,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.054922008309743,
    "equal_rewards": -2.0390208869127253,
    "random_rewards": -1.9474348459468875,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0137817837106193,
    "equal_rewards": -2.047611373349831,
    "random_rewards": -1.0300854760487201,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0069065498927525,
    "equal_rewards": -2.0317632453720664,
    "random_rewards": -2.206775608382057,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021819330898741,
    "equal_rewards": -2.045948257988429,
    "random_rewards": -1.7776209168141737,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0079364001609377,
    "equal_rewards": -2.0557361122017728,
    "random_rewards": -2.0718741026826777,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.034477370702785,
    "equal_rewards": -2.059057796923435,
    "random_rewards": -1.982609370883058,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0436950781712446,
    "equal_rewards": -2.0380135024098576,
    "random_rewards": -2.2588005033157197,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0317576367957697,
    "equal_rewards": -2.024179694181838,
    "random_rewards": -1.9194705088225144,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0038395313931034,
    "equal_rewards": -2.0248170150895994,
    "random_rewards": -1.6435184152655833,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0040392270737026,
    "equal_rewards": -2.0307661766758285,
    "random_rewards": -2.3689036346118613,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0031706935024696,
    "equal_rewards": -2.0284693293579195,
    "random_rewards": -2.0881466991918196,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0202868940169907,
    "equal_rewards": -2.051307724889505,
    "random_rewards": -2.686359444160672,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9998700338469204,
    "equal_rewards": -2.0532466776069227,
    "random_rewards": -1.1946467581737377,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.00398972191688,
    "equal_rewards": -2.02961732970254,
    "random_rewards": -1.5140089671311423,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9662963932666189,
    "equal_rewards": -2.032355957892179,
    "random_rewards": -1.3006805866923121,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.024044569437333,
    "equal_rewards": -2.0415728091475867,
    "random_rewards": -2.390810057652396,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0430399930676293,
    "equal_rewards": -2.0120944734052046,
    "random_rewards": -1.6300937572132994,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.019292463289242,
    "equal_rewards": -2.0401595557120196,
    "random_rewards": -1.9341112490063217,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.042076904166552,
    "equal_rewards": -2.062263166624282,
    "random_rewards": -2.4424835282094186,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.028059337426415,
    "equal_rewards": -2.0657977167495125,
    "random_rewards": -1.8138711659264009,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0528175419883485,
    "equal_rewards": -2.03188648078905,
    "random_rewards": -1.6416156201978105,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0131423271667446,
    "equal_rewards": -2.0420212704200678,
    "random_rewards": -2.366972986140774,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0464580684320257,
    "equal_rewards": -2.013382853055284,
    "random_rewards": -1.455430596385489,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.014356692818475,
    "equal_rewards": -2.003069307255056,
    "random_rewards": -1.6257576221225702,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0017836900663335,
    "equal_rewards": -2.055153098637467,
    "random_rewards": -1.6169168523424204,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000753519994105,
    "equal_rewards": -2.0524726803216904,
    "random_rewards": -1.5034066069662937,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007361399118878,
    "equal_rewards": -2.0366108842841424,
    "random_rewards": -1.8150604755992457,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.997523326280403,
    "equal_rewards": -2.022421136377594,
    "random_rewards": -1.5000047200818392,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9826359117082384,
    "equal_rewards": -2.0242717371880703,
    "random_rewards": -2.525487740437133,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.003892770427804,
    "equal_rewards": -2.0297469693907644,
    "random_rewards": -1.660975876807959,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0096372660966875,
    "equal_rewards": -2.036775390368616,
    "random_rewards": -2.203844249630767,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000397790351655,
    "equal_rewards": -2.0543461676572075,
    "random_rewards": -1.1654998739938498,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.050115674568729,
    "equal_rewards": -2.0316069940570527,
    "random_rewards": -1.9347891906430874,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0055212721987683,
    "equal_rewards": -2.0463173407430357,
    "random_rewards": -2.2366470934949287,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.016746906439902,
    "equal_rewards": -2.0365314960649474,
    "random_rewards": -1.2303728539970966,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0496539253463144,
    "equal_rewards": -2.045114422705271,
    "random_rewards": -1.374832468932416,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0491850255086894,
    "equal_rewards": -2.033104333174189,
    "random_rewards": -1.6560196124518838,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.023985032284217,
    "equal_rewards": -2.058802106520497,
    "random_rewards": -1.340387543305253,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0339076222464354,
    "equal_rewards": -2.0153900604578325,
    "random_rewards": -0.8694637777386881,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0490651232065065,
    "equal_rewards": -2.0166763090011974,
    "random_rewards": -1.0300175885379028,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.99963449841325,
    "equal_rewards": -2.046637537300658,
    "random_rewards": -1.9555514964438787,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.014783868697246,
    "equal_rewards": -2.0449842507494256,
    "random_rewards": -2.5510209283398,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.017698944377105,
    "equal_rewards": -2.042648054760753,
    "random_rewards": -1.8217741854963525,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0170139966366554,
    "equal_rewards": -2.042452362089331,
    "random_rewards": -1.6705297445807439,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.032942434039369,
    "equal_rewards": -2.0582323011615697,
    "random_rewards": -2.409031504786085,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011478910687928,
    "equal_rewards": -2.0698903492526393,
    "random_rewards": -2.2765124085524366,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.023959459374145,
    "equal_rewards": -2.0533885724628322,
    "random_rewards": -1.652025947557274,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0052634124995663,
    "equal_rewards": -2.059490289946658,
    "random_rewards": -1.4685671414261225,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.005575262524889,
    "equal_rewards": -2.0587994798972074,
    "random_rewards": -3.0206106100928114,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.031496822403306,
    "equal_rewards": -2.0440426453950753,
    "random_rewards": -2.212934957939942,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.01010198498522,
    "equal_rewards": -2.0217857875464844,
    "random_rewards": -1.8117836950173292,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.031517446784532,
    "equal_rewards": -2.0055038829489686,
    "random_rewards": -1.0281117595540643,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011161890944796,
    "equal_rewards": -2.0621320602424578,
    "random_rewards": -2.118086603957602,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.018595862222606,
    "equal_rewards": -2.04333187113211,
    "random_rewards": -1.0525591266935057,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.008121122594115,
    "equal_rewards": -2.0622955315486804,
    "random_rewards": -1.360952667450647,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0356114137884256,
    "equal_rewards": -2.022450763959503,
    "random_rewards": -1.490760003716721,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9992719504511989,
    "equal_rewards": -2.0325090504032444,
    "random_rewards": -1.3369842416376956,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0303840779201323,
    "equal_rewards": -2.017039263304348,
    "random_rewards": -1.3097417975457075,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9865461393488002,
    "equal_rewards": -2.0204392834900187,
    "random_rewards": -1.184704079075186,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0206230195280313,
    "equal_rewards": -2.0476082064855397,
    "random_rewards": -1.5192217586394519,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0269591959305435,
    "equal_rewards": -2.0561296650126764,
    "random_rewards": -2.692270689938173,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0398777000679904,
    "equal_rewards": -2.0615221162244493,
    "random_rewards": -2.2416367435379847,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0497254412964456,
    "equal_rewards": -2.0328498501449674,
    "random_rewards": -1.4643928237347672,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9903355685134019,
    "equal_rewards": -2.0172947022354752,
    "random_rewards": -1.657915901438944,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.977037329946382,
    "equal_rewards": -2.043660075648786,
    "random_rewards": -1.968198783041835,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.018334708552417,
    "equal_rewards": -2.0687286615786222,
    "random_rewards": -1.8542936256352367,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0558203452666617,
    "equal_rewards": -2.040315900284095,
    "random_rewards": -1.9181938606227211,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0304135818332996,
    "equal_rewards": -2.0612756597698634,
    "random_rewards": -1.4786872835993823,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0489869766018516,
    "equal_rewards": -2.0298371553680425,
    "random_rewards": -2.3538093003331735,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0357619418062756,
    "equal_rewards": -2.0230794933937486,
    "random_rewards": -1.8947195834309278,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9800588046307916,
    "equal_rewards": -2.0485164644565494,
    "random_rewards": -1.3777341380120198,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.041330428022672,
    "equal_rewards": -2.0364875143826335,
    "random_rewards": -2.3921756353601182,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0191567637701024,
    "equal_rewards": -2.0011725320512896,
    "random_rewards": -1.1959493136914627,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.992267880310332,
    "equal_rewards": -2.047454742071356,
    "random_rewards": -1.4969662708681244,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.001671990182876,
    "equal_rewards": -2.0506363463361135,
    "random_rewards": -2.264889682188948,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.02328717015846,
    "equal_rewards": -2.0462519887137645,
    "random_rewards": -0.7409911146774122,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007329100709835,
    "equal_rewards": -2.060298028634869,
    "random_rewards": -1.837472787708303,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.052175399443243,
    "equal_rewards": -2.0366298435931154,
    "random_rewards": -1.9622373564536997,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.04286552222627,
    "equal_rewards": -2.038004081882912,
    "random_rewards": -1.8071107261318453,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.011512448549604,
    "equal_rewards": -2.0576443998587624,
    "random_rewards": -1.8155866714845645,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.048829249855653,
    "equal_rewards": -2.0134117187564593,
    "random_rewards": -2.2237327614286357,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0457181451818998,
    "equal_rewards": -2.0259415420724354,
    "random_rewards": -2.8073204782773464,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0562283782860917,
    "equal_rewards": -2.0198273562334577,
    "random_rewards": -1.4973994889234583,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0312734182650063,
    "equal_rewards": -2.0615718880717724,
    "random_rewards": -1.1848703877304043,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0667598555775415,
    "equal_rewards": -2.0384017971328543,
    "random_rewards": -1.5022315621659414,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.03436702077995,
    "equal_rewards": -2.0593438373197452,
    "random_rewards": -2.3969104276437267,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.003920641828906,
    "equal_rewards": -2.067001700173018,
    "random_rewards": -1.7858260196525093,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000559262745594,
    "equal_rewards": -2.051936989050538,
    "random_rewards": -2.68732989846,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9910332266338213,
    "equal_rewards": -2.035362541487454,
    "random_rewards": -2.4037113901339553,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.990139915223636,
    "equal_rewards": -2.0454320927911285,
    "random_rewards": -2.7179186747029234,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.014426772165328,
    "equal_rewards": -2.0453326708875843,
    "random_rewards": -2.117754346683783,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0004742545060075,
    "equal_rewards": -2.0332546002111713,
    "random_rewards": -1.9491620140512134,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0033703486016305,
    "equal_rewards": -2.020382695246779,
    "random_rewards": -1.0167970853121955,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0282658899691346,
    "equal_rewards": -2.0532566126101957,
    "random_rewards": -2.439229009726744,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0395278040950386,
    "equal_rewards": -2.022760789854993,
    "random_rewards": -1.591769520598165,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.025665435366925,
    "equal_rewards": -2.006842550422041,
    "random_rewards": -2.942272534236431,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0358987717848867,
    "equal_rewards": -2.022231617946218,
    "random_rewards": -2.076293748067595,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9986810162589579,
    "equal_rewards": -2.0526093179045675,
    "random_rewards": -1.9311643373407283,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.998906165928581,
    "equal_rewards": -2.033792194117807,
    "random_rewards": -1.1676641747668808,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.027731358041564,
    "equal_rewards": -2.0073523389909878,
    "random_rewards": -2.4829569728397405,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.978977840367735,
    "equal_rewards": -2.0471451733976718,
    "random_rewards": -2.543529006874253,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021558702874769,
    "equal_rewards": -2.074981790971263,
    "random_rewards": -1.6680882963209287,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021537494937531,
    "equal_rewards": -2.0394411998756103,
    "random_rewards": -1.365546238163727,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.024080244729327,
    "equal_rewards": -2.015758753146391,
    "random_rewards": -2.5099428293008614,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.010465709453153,
    "equal_rewards": -2.061065224271802,
    "random_rewards": -1.3941104544999554,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.039602046912292,
    "equal_rewards": -2.0301843618471866,
    "random_rewards": -1.921763354419316,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.036139173792802,
    "equal_rewards": -2.0182039554234166,
    "random_rewards": -1.899494245684701,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0148470236231457,
    "equal_rewards": -2.043590797432298,
    "random_rewards": -1.5266460668375552,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.925714826957186,
    "equal_rewards": -1.971427696818067,
    "random_rewards": -0.7046146413393227,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.974466332201462,
    "equal_rewards": -1.9946511375893008,
    "random_rewards": -0.5802881730023304,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0646112669256738,
    "equal_rewards": -2.039015568055615,
    "random_rewards": -1.329925201518573,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.038441122941605,
    "equal_rewards": -2.0613367580328252,
    "random_rewards": -2.1334510038747125,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0018382611222636,
    "equal_rewards": -2.0627898374526925,
    "random_rewards": -1.9814899806759891,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0010275374221758,
    "equal_rewards": -2.0491899822906285,
    "random_rewards": -2.4134607287102554,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.999587237360088,
    "equal_rewards": -2.05261506457687,
    "random_rewards": -0.7586570223532397,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0623225555589046,
    "equal_rewards": -2.0310993785592903,
    "random_rewards": -2.2403076323011364,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9949189742003983,
    "equal_rewards": -2.026130067964045,
    "random_rewards": -1.4439262170415637,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9957072633238755,
    "equal_rewards": -2.028487411218979,
    "random_rewards": -1.8984915662989899,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.014029011760296,
    "equal_rewards": -2.0311194129932058,
    "random_rewards": -1.2953884774097864,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0286179393559856,
    "equal_rewards": -2.008761264310933,
    "random_rewards": -1.1914334815399645,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9911138728704987,
    "equal_rewards": -2.044447774199388,
    "random_rewards": -1.5099870682964298,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9996912710207904,
    "equal_rewards": -2.0399190356295236,
    "random_rewards": -1.6494795463957694,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.015580561833667,
    "equal_rewards": -2.00016683266466,
    "random_rewards": -1.0135442803975223,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9942662129128532,
    "equal_rewards": -2.0424857463602892,
    "random_rewards": -1.0534958512140373,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.041114766510079,
    "equal_rewards": -2.0321465482912267,
    "random_rewards": -2.091215339360687,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.997906934436336,
    "equal_rewards": -2.0539143601716088,
    "random_rewards": -1.6507795674110517,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9946498164012305,
    "equal_rewards": -2.0420114740762862,
    "random_rewards": -1.4581617826575393,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.021466551445013,
    "equal_rewards": -2.0413800171404137,
    "random_rewards": -2.1088652490334607,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.006812486523444,
    "equal_rewards": -2.074136266233783,
    "random_rewards": -2.1126761034829045,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0161292013809478,
    "equal_rewards": -2.048673105931656,
    "random_rewards": -1.1996170417365306,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.018880549325491,
    "equal_rewards": -1.9958753636788766,
    "random_rewards": -2.1829923393782424,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0075337686953065,
    "equal_rewards": -2.0234220990105762,
    "random_rewards": -2.3619558873682593,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0141740291259906,
    "equal_rewards": -2.0319103235122666,
    "random_rewards": -2.238699951675404,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0092443631641643,
    "equal_rewards": -2.047467085499782,
    "random_rewards": -1.807998077964049,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.022965710016479,
    "equal_rewards": -2.0514352583030173,
    "random_rewards": -1.8161999097530983,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0436282871940197,
    "equal_rewards": -2.021768175995037,
    "random_rewards": -1.6394744559895653,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0170140522552633,
    "equal_rewards": -2.043464601278541,
    "random_rewards": -1.471699506332603,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.94913931177433,
    "equal_rewards": -2.0192087220332704,
    "random_rewards": -1.1516084979442924,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9601170979614315,
    "equal_rewards": -1.927956263197729,
    "random_rewards": -1.8686314845575995,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9571697055604522,
    "equal_rewards": -1.9904040737498256,
    "random_rewards": -1.0010979847582555,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0141185125044863,
    "equal_rewards": -2.0481372520026424,
    "random_rewards": -2.557928780843252,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0282492359784197,
    "equal_rewards": -2.0535730389641493,
    "random_rewards": -2.7063796964300866,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.009847942694364,
    "equal_rewards": -2.0636139144891787,
    "random_rewards": -1.6755323926375754,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0538203784874147,
    "equal_rewards": -2.0251837542637494,
    "random_rewards": -1.4654946148692236,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.002534467676609,
    "equal_rewards": -2.0070092714794705,
    "random_rewards": -1.306521453906477,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9572509608659976,
    "equal_rewards": -2.0108847327851254,
    "random_rewards": -1.7819438374084844,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.043666412127448,
    "equal_rewards": -2.027596430129848,
    "random_rewards": -1.788352880340412,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0062876511134595,
    "equal_rewards": -2.063571163951555,
    "random_rewards": -1.0727659626724004,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0132703534012735,
    "equal_rewards": -2.016905032087603,
    "random_rewards": -2.3686983772755688,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9721974615234235,
    "equal_rewards": -1.99705173792879,
    "random_rewards": -1.6279160494411422,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0073952535821724,
    "equal_rewards": -2.070352317455324,
    "random_rewards": -1.360069203915868,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9860065145842065,
    "equal_rewards": -2.0420210079199945,
    "random_rewards": -1.688441680434614,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9952404446476852,
    "equal_rewards": -1.9749253815989554,
    "random_rewards": -1.9018032092689854,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9928596278663684,
    "equal_rewards": -2.0141290824855718,
    "random_rewards": -0.5945599892882358,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9920667728439658,
    "equal_rewards": -2.039737963465725,
    "random_rewards": -1.8053304840390267,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.044061086147155,
    "equal_rewards": -2.019440846572385,
    "random_rewards": -1.7955526275856686,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9910953901935318,
    "equal_rewards": -2.04521479729884,
    "random_rewards": -1.4900609170090289,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9618991731658721,
    "equal_rewards": -1.9928538193759895,
    "random_rewards": -0.5821249440552314,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9621517077010655,
    "equal_rewards": -2.0013627410008477,
    "random_rewards": -1.338748732251891,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0170978190982716,
    "equal_rewards": -1.9846887167290692,
    "random_rewards": -1.613602289597687,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9772294250234193,
    "equal_rewards": -2.00331980833128,
    "random_rewards": -1.1637977293227848,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9194484257329187,
    "equal_rewards": -1.9907861515452177,
    "random_rewards": -2.4577924231811714,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9047044282167371,
    "equal_rewards": -1.9449622449376323,
    "random_rewards": -1.2514130634567924,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.980489361816955,
    "equal_rewards": -1.9420937868794885,
    "random_rewards": -2.144858104640011,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9866786059778523,
    "equal_rewards": -1.9742856266922901,
    "random_rewards": -0.8755704335771157,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9793777355703144,
    "equal_rewards": -2.001894468288571,
    "random_rewards": -1.1567416246065079,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0319651212212944,
    "equal_rewards": -2.0159742074012432,
    "random_rewards": -0.44253092357588264,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.985092686680159,
    "equal_rewards": -2.0331079675597543,
    "random_rewards": -2.5508542521766207,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0092573238986104,
    "equal_rewards": -2.032254923857212,
    "random_rewards": -1.3820356425293587,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9793237662468128,
    "equal_rewards": -2.0341073698459122,
    "random_rewards": -1.606055866485812,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9953124797968467,
    "equal_rewards": -2.009594032728603,
    "random_rewards": -1.1977363568059571,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9577303718557348,
    "equal_rewards": -2.0214715998020694,
    "random_rewards": -1.3078967631271778,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9590766423886679,
    "equal_rewards": -2.0174370196452647,
    "random_rewards": -2.6502809574564075,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9494557641821242,
    "equal_rewards": -1.9798583964052714,
    "random_rewards": -1.1737030926069065,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9446176611218702,
    "equal_rewards": -2.0018382455466646,
    "random_rewards": -2.044540150327728,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9947854004532841,
    "equal_rewards": -2.0551628710230894,
    "random_rewards": -2.086570526292451,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0280520159721043,
    "equal_rewards": -2.02379602445707,
    "random_rewards": -0.9092051124595351,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0161966385247276,
    "equal_rewards": -1.9968795698393187,
    "random_rewards": -2.0339624032370223,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.019149058386305,
    "equal_rewards": -1.9984160448003583,
    "random_rewards": -2.4577892099782197,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9845462168232495,
    "equal_rewards": -2.050784600695117,
    "random_rewards": -1.9293460861775658,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000995687707131,
    "equal_rewards": -2.013132238745759,
    "random_rewards": -1.3138294026106732,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0293278044018312,
    "equal_rewards": -1.9995471334190422,
    "random_rewards": -2.9257617106609373,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0268128393619973,
    "equal_rewards": -2.0521769293202494,
    "random_rewards": -2.2807166331710773,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0433148643442576,
    "equal_rewards": -2.0279582212007097,
    "random_rewards": -1.7772318339385356,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.000869944032984,
    "equal_rewards": -2.062750206806077,
    "random_rewards": -2.1231631539811913,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.030443652359055,
    "equal_rewards": -2.055639194598269,
    "random_rewards": -1.9499320742406705,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0524396780966434,
    "equal_rewards": -2.018455725112404,
    "random_rewards": -2.9542766862099543,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.993496663269309,
    "equal_rewards": -2.0276163159454423,
    "random_rewards": -2.3584660790939758,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0153233165891327,
    "equal_rewards": -2.041953848619459,
    "random_rewards": -0.8958830214170534,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0106891286461788,
    "equal_rewards": -2.031917814990123,
    "random_rewards": -2.2417805721482584,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9956552627882105,
    "equal_rewards": -2.0499530892530666,
    "random_rewards": -2.2398782006699984,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0080329224950138,
    "equal_rewards": -2.055203070793691,
    "random_rewards": -2.541310339158725,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.030240087496643,
    "equal_rewards": -2.0539389556766343,
    "random_rewards": -2.2819041675832756,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.044576484429937,
    "equal_rewards": -2.024528690967249,
    "random_rewards": -2.2162151393602656,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0131555927583342,
    "equal_rewards": -2.052748335824737,
    "random_rewards": -1.9817574163541583,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.050579773056984,
    "equal_rewards": -2.034578725399144,
    "random_rewards": -1.4691192845504617,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.002766133166089,
    "equal_rewards": -2.058761964168433,
    "random_rewards": -2.258116842985226,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.036613507045528,
    "equal_rewards": -2.028919555436011,
    "random_rewards": -1.3478537806835797,
    "optimal": 0
  },
  {
    "reward_this_epoch": -1.9932175389354791,
    "equal_rewards": -2.004872006288741,
    "random_rewards": -1.446576316635992,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0030218280218497,
    "equal_rewards": -2.0316025769765487,
    "random_rewards": -1.9110279053955446,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0115680589659553,
    "equal_rewards": -2.074558968479766,
    "random_rewards": -2.400512632163768,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0195747153376136,
    "equal_rewards": -2.0723986008045343,
    "random_rewards": -1.507359527601173,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0144158475878875,
    "equal_rewards": -2.0658185924949475,
    "random_rewards": -1.328593832474532,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.033028177131447,
    "equal_rewards": -2.0576078665199455,
    "random_rewards": -1.6566367041083563,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.038602806857427,
    "equal_rewards": -2.04735662858305,
    "random_rewards": -1.3559392043183929,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.007727837541411,
    "equal_rewards": -2.0452402126290985,
    "random_rewards": -2.2368403714466862,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0177790638527116,
    "equal_rewards": -2.0020062523096973,
    "random_rewards": -1.027702488504485,
    "optimal": 0
  },
  {
    "reward_this_epoch": -2.0364183974103636,
    "equal_rewards": -2.0327675294494236,
    "random_rewards": -1.9075809040561031,
    "optimal": 0
  }
]