step,training/mean_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward 500,-0.1030593141913414,4.998979114532471,, 1000,-0.0991375744342804,4.995057356834412,, 1500,-0.0841103345155716,4.98003011226654,, 2000,-0.0835295245051384,4.979449323654174,, 2500,-0.04887982830405235,4.944799632072448,, 3000,-0.05825298652052879,4.954172759056092,, 3500,-0.05094769597053528,4.946867492675781,, 4000,-0.07958874851465225,4.975508554458618,, 4500,-0.023159397765994072,4.919079197883606,, 5000,-0.03175611421465874,4.927675925254822,, 5000,,,4.785908479690551,0.11001132011413574 5500,-0.020329216495156288,4.916249018669128,, 6000,-0.03106863982975483,4.926988430976868,, 6500,0.004000409506261349,4.891919390678406,, 7000,0.023376112803816795,4.872543700218201,, 7500,0.03979581594467163,4.856123989105225,, 8000,0.028650594875216484,4.8672692227363585,, 8500,0.036675047129392624,4.859244741439819,, 9000,0.062382012605667114,4.83353777885437,, 9500,0.06964697688817978,4.826272831916809,, 10000,0.04688073694705963,4.849039092540741,, 10000,,,4.664253759384155,0.23166604042053224 10500,0.09395117312669754,4.801968657970429,, 11000,0.07559625059366226,4.820323540210724,, 11500,0.07523959130048752,4.820680227279663,, 12000,0.09003405272960663,4.805885802268982,, 12500,0.06658325344324112,4.829336522102356,, 13000,0.10671908408403397,4.789200759887695,, 13500,0.13387431204319,4.762045419692993,, 14000,0.09571521729230881,4.800204495429993,, 14500,0.12774603068828583,4.7681736941337585,, 15000,0.1551055908203125,4.740814234733581,, 15000,,,4.511654605865479,0.384265193939209 15500,0.19235555827617645,4.703564257621765,, 16000,0.1678125560283661,4.728107197761536,, 16500,0.14357946813106537,4.752340325832367,, 17000,0.1765490174293518,4.719370777606964,, 17500,0.18312819302082062,4.712791594028473,, 18000,0.18223120272159576,4.713688601016998,, 18500,0.17247970402240753,4.723440147399902,, 19000,0.2236843854188919,4.672235408782959,, 19500,0.15784390270709991,4.738075869083405,, 20000,0.20917044579982758,4.686749482631684,, 20000,,,4.467903714179993,0.42801608562469484 20500,0.22862859070301056,4.667291256427765,, 21000,0.24906033277511597,4.6468594727516175,, 21500,0.23543593287467957,4.66048385810852,, 22000,0.26465317606925964,4.631266430854797,, 22500,0.26369884610176086,4.632220963001251,, 23000,0.2929648756980896,4.602955040454865,, 23500,0.23437939584255219,4.661540421009064,, 24000,0.2750856876373291,4.620834246635437,, 24500,0.2519882023334503,4.64393159198761,, 25000,0.28582215309143066,4.610097687721252,, 25000,,,4.424220185279847,0.4716996145248413 25500,0.30801859498023987,4.587901228904724,, 26000,0.275161474943161,4.62075852060318,, 26500,0.2558456361293793,4.640074174880981,, 27000,0.34105029702186584,4.554869527339935,, 27500,0.28095781803131104,4.614961975097656,, 28000,0.3148139715194702,4.581105699539185,, 28500,0.3440060317516327,4.551913905620575,, 29000,0.346234530210495,4.5496852869987485,, 29500,0.339945524930954,4.555974395751953,, 30000,0.31798580288887024,4.577933970451355,, 30000,,,4.379466395378113,0.5164534044265747 30500,0.32665199041366577,4.569267924785614,, 31000,0.3462222218513489,4.549697573184967,, 31500,0.35960492491722107,4.536315152645111,, 32000,0.3347339332103729,4.56118608379364,, 32500,0.3494201600551605,4.546499630451202,, 33000,0.4554063677787781,4.440513319015503,, 33500,0.38216596841812134,4.5137539792060855,, 34000,0.44636884331703186,4.449550995826721,, 34500,0.39428046345710754,4.5016391882896425,, 35000,0.4151197373867035,4.480799901008606,, 35000,,,4.312512676715851,0.5834071230888367 35500,0.43126583099365234,4.464653991699219,, 36000,0.43175312876701355,4.464166608333588,, 36500,0.380765438079834,4.515154520988465,, 37000,0.4076917767524719,4.488228128910064,, 37500,0.430675745010376,4.465243988037109,, 38000,0.4017561674118042,4.494163535118103,, 38500,0.47341716289520264,4.422502459526062,, 39000,0.4809066355228424,4.415013299942016,, 39500,0.5019765496253967,4.393943515300751,, 40000,0.4226892590522766,4.47323052406311,, 40000,,,4.12407511472702,0.7718446850776672 40500,0.4679238200187683,4.427995963573456,, 41000,0.459018349647522,4.436901454925537,, 41500,0.49436360597610474,4.401556460380554,, 42000,0.5523695945739746,4.343550332069397,, 42500,0.43106609582901,4.464853503227234,, 43000,0.4544079601764679,4.4415118060112,, 43500,0.5510848760604858,4.344834839344025,, 44000,0.49370697140693665,4.402212840080261,, 44500,0.46137377619743347,4.434546278476715,, 45000,0.5532727837562561,4.342647000312805,, 45000,,,4.141054537296295,0.7548652625083924 45500,0.49406886100769043,4.4018512125015254,, 46000,0.563704788684845,4.332215304851532,, 46500,0.5523806214332581,4.3435388956069945,, 47000,0.5605859756469727,4.33533410692215,, 47500,0.5262837409973145,4.369635868549347,, 48000,0.5978171825408936,4.298102495193482,, 48500,0.5708543062210083,4.325065383911133,, 49000,0.6022892594337463,4.293630569458008,, 49500,0.6121063828468323,4.283813173770905,, 50000,0.6365397572517395,4.259379854679108,, 50000,,,4.091523807048798,0.8043959927558899 50500,0.6499400734901428,4.245979862689972,, 51000,0.6369622945785522,4.258957699775696,,