| step,training/mean_reward,training/mean_global_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward | |
| 500,0.10138962417840958,0.10138964605331421,4.793609381198883,, | |
| 1000,0.32100710272789,0.3210071797370911,4.5739918475151065,, | |
| 1500,0.46338993310928345,0.4633899073600769,4.43160911989212,, | |
| 2000,0.6104784607887268,0.6104782929420471,4.28452073431015,, | |
| 2500,0.703420102596283,0.7034200735092163,4.191578953742981,, | |
| 3000,0.6190058588981628,0.6190059309005738,4.275993096351623,, | |
| 3500,0.7363145351409912,0.7363144817352295,4.158684545516968,, | |
| 4000,0.7681872844696045,0.7681872429847717,4.126811784267425,, | |
| 4500,0.7203475832939148,0.7203476023674011,4.174651424884797,, | |
| 5000,0.6513270735740662,0.6513269896507263,4.243672037601471,, | |
| 5000,,,,4.285640616416931,0.6093583703041077 | |
| 5500,0.6670124530792236,0.6670126585960389,4.2279863686561585,, | |
| 6000,0.5963553786277771,0.5963553357124328,4.298643691539764,, | |
| 6500,0.7398293614387512,0.7398292517662048,4.155169775485993,, | |
| 7000,0.7350034713745117,0.7350035715103149,4.159995455741882,, | |
| 7500,0.6802617907524109,0.6802616105079651,4.214737416744232,, | |
| 8000,0.625156581401825,0.6251564984321594,4.269842528820038,, | |
| 8500,0.7493157386779785,0.7493159060478211,4.145683121204376,, | |
| 9000,0.6767943501472473,0.6767941274642945,4.218204899787903,, | |
| 9500,0.6911408305168152,0.6911408333778382,4.2038581938743596,, | |
| 10000,0.6816282272338867,0.6816284265518189,4.213370600700379,, | |
| 10000,,,,4.209020570516587,0.685978353023529 | |
| 10500,0.8478944897651672,0.8478943705558777,4.04710465669632,, | |
| 11000,0.7896162271499634,0.7896162571907044,4.105382770061493,, | |
| 11500,0.6947903037071228,0.6947902188301086,4.200208808422088,, | |
| 12000,0.8020890951156616,0.8020889682769775,4.09291005897522,, | |
| 12500,0.7868940830230713,0.7868941340446473,4.10810489320755,, | |
| 13000,0.8571906685829163,0.8571908102035523,4.037808217048645,, | |
| 13500,0.7242065668106079,0.7242065687179565,4.17079245853424,, | |
| 14000,0.7075560688972473,0.7075559868812561,4.187443040370941,, | |
| 14500,0.6317536234855652,0.6317536654472351,4.263245361804962,, | |
| 15000,0.7987551689147949,0.7987551894187928,4.096243837833405,, | |
| 15000,,,,4.27228999376297,0.6227089762687683 | |
| 15500,0.79903644323349,0.799036404132843,4.095962623119354,, | |
| 16000,0.8117448687553406,0.8117447996139526,4.083254227638244,, | |
| 16500,0.7866731286048889,0.7866731686592102,4.108325858592987,, | |
| 17000,0.7090850472450256,0.7090849604606628,4.185914066791534,, | |
| 17500,0.7202248573303223,0.7202249927520752,4.174774034500122,, | |
| 18000,0.7214937210083008,0.7214936652183532,4.173505362033844,, | |
| 18500,0.6860231161117554,0.6860232176780701,4.208975809574127,, | |
| 19000,0.75033038854599,0.7503303017616272,4.14466872549057,, | |
| 19500,0.6601693034172058,0.6601692628860474,4.23482976436615,, | |
| 20000,0.7293099761009216,0.7293100237846375,4.16568900346756,, | |
| 20000,,,,4.288608310222625,0.6063905954360962 | |
| 20500,0.6952121257781982,0.6952121315002442,4.199786895751953,, | |
| 21000,0.7251101136207581,0.7251100993156433,4.169888927936554,, | |
| 21500,0.6353460550308228,0.6353460865020752,4.259652940750122,, | |
| 22000,0.729763925075531,0.7297638411521912,4.1652351861000065,, | |
| 22500,0.5897969603538513,0.5897969045639038,4.305202122688294,, | |
| 23000,0.6977773308753967,0.6977774090766907,4.197221618175506,, | |
| 23500,0.7072116136550903,0.7072114667892456,4.187787560462952,, | |
| 24000,0.6394088864326477,0.6394088034629821,4.255590223789215,, | |
| 24500,0.6553497910499573,0.6553498525619507,4.239649174690246,, | |
| 25000,0.7058669924736023,0.7058668637275696,4.1891321635246275,, | |
| 25000,,,,4.2546837043762205,0.6403152346611023 | |
| 25500,0.6849509477615356,0.68495103931427,4.210047987937927,, | |
| 26000,0.6139134168624878,0.6139133796691895,4.281085647583008,, | |
| 26500,0.639238715171814,0.6392387528419494,4.255760274410248,, | |
| 27000,0.7127382159233093,0.7127382731437684,4.182260754108429,, | |
| 27500,0.6135566234588623,0.61355668592453,4.281442341327668,, | |
| 28000,0.6666881442070007,0.6666881637573242,4.228310863494873,, | |
| 28500,0.6212300658226013,0.621230149269104,4.273768877983093,, | |
| 29000,0.6808567643165588,0.6808567790985107,4.214142248153687,, | |
| 29500,0.6208623051643372,0.6208624396324157,4.274136587619782,, | |
| 30000,0.5698662400245667,0.5698662033081054,4.325132823944092,, | |
| 30000,,,,4.314021747112275,0.580977201461792 | |
| 30500,0.573557436466217,0.5735573797225952,4.3214416475296025,, | |
| 31000,0.6417831778526306,0.6417831826210022,4.253215844631195,, | |
| 31500,0.6426482796669006,0.6426482419967652,4.252350785255432,, | |
| 32000,0.6424336433410645,0.6424335031509399,4.252565524101257,, | |
| 32500,0.6704631447792053,0.6704632639884949,4.224535763263702,, | |
| 33000,0.6691726446151733,0.6691728472709656,4.225826179981231,, | |
| 33500,0.6270766258239746,0.6270764141082764,4.267922613143921,, | |
| 34000,0.6727749705314636,0.6727748069763183,4.222224220275879,, | |
| 34500,0.7279649972915649,0.7279651560783387,4.167033871173858,, | |
| 35000,0.6042982935905457,0.6042982454299927,4.2907007818222045,, | |
| 35000,,,,4.2093222713470455,0.6856765747070312 | |
| 35500,0.7066655158996582,0.7066656355857849,4.188333391666412,, | |
| 36000,0.6421645879745483,0.6421645250320435,4.2528345022201535,, | |
| 36500,0.6296740174293518,0.6296738610267639,4.265325166225433,, | |
| 37000,0.668488085269928,0.6684881248474122,4.226510902404785,, | |
| 37500,0.6179291009902954,0.6179290752410889,4.277069952011108,, | |
| 38000,0.6326427459716797,0.6326426672935486,4.262356359958648,, | |
| 38500,0.6458050608634949,0.6458048853874206,4.249194141864777,, | |
| 39000,0.612914502620697,0.6129144105911255,4.282084616661072,, | |
| 39500,0.6920642852783203,0.6920640897750855,4.202934937477112,, | |
| 40000,0.5515623092651367,0.5515623660087585,4.343436661243438,, | |
| 40000,,,,4.303088793754577,0.5919101238250732 | |
| 40500,0.5980678796768188,0.5980677924156189,4.2969312348365785,, | |
| 41000,0.6581017971038818,0.6581018686294555,4.2368971586227415,, | |
| 41500,0.6260193586349487,0.6260193209648133,4.268979706287384,, | |
| 42000,0.672907829284668,0.6729078931808472,4.22209113407135,, | |
| 42500,0.6085816621780396,0.6085818328857422,4.2864171943664555,, | |
| 43000,0.7214232683181763,0.7214230508804321,4.173575976371765,, | |
| 43500,0.7285151481628418,0.7285150332450867,4.166483994007111,, | |
| 44000,0.6737976670265198,0.6737977070808411,4.221201320171356,, | |
| 44500,0.6932497024536133,0.6932497229576111,4.201749304294586,, | |
| 45000,0.666674017906189,0.666673834323883,4.228325192928314,, | |
| 45000,,,,4.311138348579407,0.5838605761528015 | |
| 45500,0.7553684711456299,0.7553685283660889,4.139630498886109,, | |
| 46000,0.6021735072135925,0.60217347574234,4.292825551509857,, | |
| 46500,0.6395912766456604,0.6395911550521851,4.255407872200013,, | |
| 47000,0.5873399972915649,0.5873401184082031,4.307658908843994,, | |
| 47500,0.7340129613876343,0.7340131001472473,4.16098592710495,, | |
| 48000,0.6702156662940979,0.6702154622077942,4.224783565044403,, | |
| 48500,0.6382197737693787,0.6382196388244629,4.256779388427734,, | |
| 49000,0.7342012524604797,0.7342013144493102,4.160797712802887,, | |
| 49500,0.6475066542625427,0.6475066475868225,4.247492379665375,, | |
| 50000,0.688629150390625,0.688629168510437,4.20636985874176,, | |
| 50000,,,,4.156364495754242,0.7386343479156494 | |