| step,training/mean_reward,training/mean_global_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward | |
| 500,-0.07778409868478775,-0.07778412127494812,4.9737038908004765,, | |
| 1000,-0.07308678328990936,-0.07308683681488037,4.9690066452026365,, | |
| 1500,-0.0725506991147995,-0.07255078029632568,4.968470588684082,, | |
| 2000,-0.07701226323843002,-0.0770123405456543,4.97293214225769,, | |
| 2500,-0.06356993317604065,-0.0635700546503067,4.959489857673645,, | |
| 3000,-0.06562785804271698,-0.06562787055969238,4.961547649383545,, | |
| 3500,-0.08410661667585373,-0.08410661661624909,4.980026405334472,, | |
| 4000,-0.08508188277482986,-0.08508182775974274,4.981001621246338,, | |
| 4500,-0.0697481781244278,-0.06974808943271638,4.96566790008545,, | |
| 5000,-0.05110834911465645,-0.05110851192474365,4.947028332710266,, | |
| 5000,,,,4.867484593391419,0.028435036540031433 | |
| 5500,-0.04785158857703209,-0.047851468086242674,4.943771250724793,, | |
| 6000,-0.07173934578895569,-0.07173929059505463,4.967659108638763,, | |
| 6500,-0.048170268535614014,-0.04817038571834564,4.94409019947052,, | |
| 7000,-0.04459132254123688,-0.04459130954742432,4.940511101722717,, | |
| 7500,-0.033345289528369904,-0.03334525680541992,4.92926508140564,, | |
| 8000,-0.022553663700819016,-0.022553648233413697,4.918473446846009,, | |
| 8500,-0.029491521418094635,-0.029491498947143556,4.925411255836487,, | |
| 9000,0.007972097024321556,0.007972009062767028,4.887947773456573,, | |
| 9500,0.02823847159743309,0.028238460779190063,4.867681334495544,, | |
| 10000,0.008590635843575,0.008590653419494628,4.887329165458679,, | |
| 10000,,,,4.789935541152954,0.10598412901163101 | |
| 10500,0.016802435740828514,0.016802422523498534,4.8791173872947695,, | |
| 11000,0.06150348111987114,0.06150336337089539,4.834416398525238,, | |
| 11500,0.06597872823476791,0.06597889864444732,4.8299408965110775,, | |
| 12000,0.06614264845848083,0.06614261496067048,4.829777156352997,, | |
| 12500,0.10290350764989853,0.10290357291698456,4.793016227722168,, | |
| 13000,0.1099155992269516,0.10991543674468994,4.78600437784195,, | |
| 13500,0.15104752779006958,0.15104750537872313,4.744872282981873,, | |
| 14000,0.11891762912273407,0.11891761374473572,4.77700218629837,, | |
| 14500,0.15114836394786835,0.15114839231967925,4.744771397590637,, | |
| 15000,0.1724139302968979,0.17241400063037873,4.723505796432495,, | |
| 15000,,,,4.539181866645813,0.35673788189888 | |
| 15500,0.18284529447555542,0.18284529280662537,4.713074505805969,, | |
| 16000,0.20016416907310486,0.20016408574581146,4.695755739688873,, | |
| 16500,0.1980336755514145,0.1980337550640106,4.6978860507011415,, | |
| 17000,0.24874335527420044,0.2487433168888092,4.647176485538482,, | |
| 17500,0.2651371955871582,0.265137153506279,4.630782650470733,, | |
| 18000,0.2869744598865509,0.2869745427370071,4.608945218086243,, | |
| 18500,0.2649194598197937,0.2649193769693375,4.631000406265259,, | |
| 19000,0.30773743987083435,0.307737366437912,4.588182416439056,, | |
| 19500,0.30824247002601624,0.30824252462387086,4.587677273273468,, | |
| 20000,0.30057528614997864,0.30057522547245025,4.5953446078300475,, | |
| 20000,,,,4.3838539004325865,0.5120658278465271 | |
| 20500,0.2937401235103607,0.29374013233184815,4.602179684638977,, | |
| 21000,0.37731263041496277,0.37731255960464477,4.518607231616974,, | |
| 21500,0.38192570209503174,0.3819256558418274,4.513994139194488,, | |
| 22000,0.41462084650993347,0.41462083864212035,4.481298965454101,, | |
| 22500,0.35952097177505493,0.3595208189487457,4.536398982524871,, | |
| 23000,0.42217838764190674,0.42217843210697176,4.473741367816925,, | |
| 23500,0.38797727227211,0.38797719073295595,4.507942622184753,, | |
| 24000,0.42756712436676025,0.4275671442747116,4.468352647781372,, | |
| 24500,0.413784921169281,0.4137848430871964,4.482134949207306,, | |
| 25000,0.42742860317230225,0.42742859745025635,4.468491202831268,, | |
| 25000,,,,4.197226531505585,0.6986932158470154 | |
| 25500,0.4359527826309204,0.43595270764827726,4.4599670896530155,, | |
| 26000,0.42954906821250916,0.42954912495613096,4.4663706350326535,, | |
| 26500,0.42300036549568176,0.4230003900527954,4.472919435501098,, | |
| 27000,0.5137567520141602,0.5137568364143371,4.382162977695465,, | |
| 27500,0.5069576501846313,0.5069576946496963,4.388962080001831,, | |
| 28000,0.45827388763427734,0.45827400410175323,4.437645796775818,, | |
| 28500,0.5107290148735046,0.5107290070056916,4.385190809726715,, | |
| 29000,0.5023621916770935,0.5023623423576355,4.393557461738586,, | |
| 29500,0.5270199179649353,0.5270199074745178,4.36889991235733,, | |
| 30000,0.50389564037323,0.5038955295085907,4.392024281024933,, | |
| 30000,,,,3.9839107620716097,0.9120090007781982 | |
| 30500,0.5310661196708679,0.5310660146474838,4.364853770256042,, | |
| 31000,0.5755795240402222,0.5755796493291855,4.32034015083313,, | |
| 31500,0.6040825843811035,0.6040827178955078,4.2918370904922485,, | |
| 32000,0.6090971231460571,0.6090972828865051,4.286822516918182,, | |
| 32500,0.6034473180770874,0.6034471817016601,4.292472598075867,, | |
| 33000,0.6097752451896667,0.609775292634964,4.286144544601441,, | |
| 33500,0.6546348929405212,0.6546350040435791,4.241284811973572,, | |
| 34000,0.65464186668396,0.6546418339014053,4.241277963638305,, | |
| 34500,0.6437334418296814,0.6437334536314011,4.2521863317489625,, | |
| 35000,0.6432875394821167,0.6432874493598938,4.252632350444793,, | |
| 35000,,,,3.8497733807563783,1.046146273612976 | |
| 35500,0.6380391120910645,0.638038902759552,4.257880887508392,, | |
| 36000,0.6645917296409607,0.6645917489528655,4.231328057289123,, | |
| 36500,0.6271026134490967,0.6271026186943054,4.268817192554474,, | |
| 37000,0.6557449698448181,0.6557447047233581,4.240175084590912,, | |
| 37500,0.640834391117096,0.6408343236446381,4.255085450172424,, | |
| 38000,0.6732937693595886,0.6732936362028122,4.22262615442276,, | |
| 38500,0.7052185535430908,0.70521850502491,4.19070130443573,, | |
| 39000,0.6906818151473999,0.6906817402839661,4.205238051891327,, | |
| 39500,0.668683648109436,0.6686836968660355,4.227236109733582,, | |
| 40000,0.6836066246032715,0.6836066318750381,4.2123131566047665,, | |
| 40000,,,,3.846012110710144,1.0499076843261719 | |
| 40500,0.6809391975402832,0.6809392216205596,4.214980579853058,, | |
| 41000,0.705655038356781,0.7056550859212876,4.190264727115631,, | |
| 41500,0.7264462113380432,0.7264462193250656,4.16947359418869,, | |
| 42000,0.7461592555046082,0.7461590821743012,4.149760719299317,, | |
| 42500,0.735652506351471,0.7356526285409928,4.1602671365737915,, | |
| 43000,0.7319276928901672,0.7319276541471481,4.1639921383857725,, | |
| 43500,0.6868069171905518,0.6868070706129074,4.209112714290619,, | |
| 44000,0.75405353307724,0.7540538147687912,4.1418659858703615,, | |
| 44500,0.7355390191078186,0.7355390584468842,4.160380744934082,, | |
| 45000,0.7395638823509216,0.7395637589693069,4.156356045246124,, | |
| 45000,,,,3.8085563659667967,1.0873632431030273 | |
| 45500,0.7695729732513428,0.7695728261470794,4.126346981525421,, | |
| 46000,0.7933635711669922,0.7933632982969284,4.102556570529938,, | |
| 46500,0.7729949355125427,0.7729948345422745,4.1229249897003175,, | |
| 47000,0.7889297008514404,0.7889297142028808,4.106990100383759,, | |
| 47500,0.7735368013381958,0.7735366115570068,4.122383196353912,, | |
| 48000,0.7912143468856812,0.7912141052484513,4.104705707550049,, | |
| 48500,0.7980750203132629,0.7980750596523285,4.097844712734222,, | |
| 49000,0.7923113107681274,0.7923115408420562,4.103608242511749,, | |
| 49500,0.7658583521842957,0.7658581597805023,4.130061641693115,, | |
| 50000,0.795021653175354,0.7950215154886245,4.100898235321045,, | |
| 50000,,,,3.8079906487464905,1.087929129600525 | |