step,training/mean_reward,training/mean_global_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward 500,0.09788089990615845,0.09788105297088623,4.798038733482361,, 1000,0.3850697875022888,0.38506973958015445,4.510850070476532,, 1500,0.4824512004852295,0.48245128500461576,4.413468507766724,, 2000,0.5128869414329529,0.5128869816064835,4.3830328192710875,, 2500,0.5754237174987793,0.5754237371683121,4.320496059894562,, 3000,0.453165739774704,0.45316576409339904,4.4427540483474735,, 3500,0.46670448780059814,0.46670447540283205,4.4292153220176695,, 4000,0.403654009103775,0.40365407371520995,4.49226571559906,, 4500,0.5576750040054321,0.5576748493909836,4.338244944572449,, 5000,0.6241496205329895,0.624149410367012,4.271770422935486,, 5000,,,,4.395808491706848,0.5001111626625061 5500,0.4967561364173889,0.49675627517700194,4.399163507461548,, 6000,0.5704429745674133,0.5704428763389587,4.325476905345917,, 6500,0.5859093070030212,0.5859093006849289,4.3100105223655705,, 7000,0.5860596299171448,0.5860596688985824,4.309860118865966,, 7500,0.5842504501342773,0.5842504538297654,4.31166934299469,, 8000,0.6242683529853821,0.6242683135271072,4.27165148639679,, 8500,0.5967080593109131,0.5967079163789749,4.299211916923523,, 9000,0.5168657302856445,0.5168655586242675,4.379054215431213,, 9500,0.4883166253566742,0.4883166671991348,4.407603135108948,, 10000,0.5411165952682495,0.5411164928674698,4.354803290367126,, 10000,,,,4.407791278362274,0.4881284534931183 10500,0.5530822277069092,0.5530822333097458,4.342837551593781,, 11000,0.543424665927887,0.5434247938394546,4.35249498462677,, 11500,0.5499421954154968,0.5499422365427017,4.345977554321289,, 12000,0.5724977850914001,0.5724978680610657,4.323421935081482,, 12500,0.46015268564224243,0.46015270829200744,4.435767088413239,, 13000,0.5012859106063843,0.5012857213020324,4.39463410949707,, 13500,0.47936245799064636,0.47936238753795624,4.416557438373566,, 14000,0.6008590459823608,0.6008591253757477,4.295060690879822,, 14500,0.5692377090454102,0.5692376000881195,4.3266821808815,, 15000,0.5777168869972229,0.5777166239023208,4.318203115940094,, 15000,,,,4.465024712085724,0.43089497089385986 15500,0.5380493998527527,0.5380493535995483,4.3578704671859745,, 16000,0.5626657605171204,0.5626656701564788,4.333254144191742,, 16500,0.5472127199172974,0.54721264731884,4.348707124710083,, 17000,0.5099992156028748,0.5099994201660156,4.385920348644256,, 17500,0.5370967388153076,0.5370967692136764,4.358823027133941,, 18000,0.6027871966362,0.6027870322465897,4.293132777690888,, 18500,0.528690755367279,0.5286908363103866,4.367228984355926,, 19000,0.5873005986213684,0.5873006213903427,4.308619173049927,, 19500,0.557671308517456,0.5576713411808014,4.338248471736908,, 20000,0.5506554245948792,0.5506554613113404,4.3452643232345585,, 20000,,,,4.334456751346588,0.5614629983901978 20500,0.5174012184143066,0.5174013067483902,4.378518506526947,, 21000,0.535306990146637,0.5353070231676101,4.3606127409935,, 21500,0.5724689364433289,0.5724689433574677,4.323450846672058,, 22000,0.5520329475402832,0.5520330629348755,4.343886743545532,, 22500,0.51885586977005,0.5188557920455933,4.377063998699188,, 23000,0.5688185095787048,0.5688184041976929,4.327101403236389,, 23500,0.5080069899559021,0.5080068889856338,4.387912935733795,, 24000,0.6024268269538879,0.6024266309738159,4.293493188858032,, 24500,0.6397639513015747,0.6397642055749894,4.256155606746674,, 25000,0.5331451296806335,0.5331450818777085,4.3627747330665585,, 25000,,,,4.333778495788574,0.5621412396430969 25500,0.5439422130584717,0.5439421247243881,4.351977682113647,, 26000,0.5997229814529419,0.599722827911377,4.296196995258331,, 26500,0.6188791990280151,0.6188790067434311,4.277040784358978,, 27000,0.5740519165992737,0.5740519139766693,4.321867904663086,, 27500,0.5875560641288757,0.5875560647249222,4.308363756656647,, 28000,0.5956392288208008,0.595639289855957,4.300280514717102,, 28500,0.6961025595664978,0.6961025722026825,4.199817235469818,, 29000,0.613887369632721,0.6138873652219773,4.282032418727875,, 29500,0.6971335411071777,0.6971336448192597,4.198786147594452,, 30000,0.6593767404556274,0.6593768185377121,4.23654297876358,, 30000,,,,4.293695793151856,0.6022239327430725 30500,0.6595940589904785,0.6595940511226654,4.236325753688813,, 31000,0.6341443657875061,0.6341443151235581,4.261775521755219,, 31500,0.6698312163352966,0.6698311214447021,4.2260886583328245,, 32000,0.7031504511833191,0.7031503174304962,4.192769515514374,, 32500,0.694156289100647,0.694156224489212,4.201763575553894,, 33000,0.7418004870414734,0.7418004893064499,4.1541192984581,, 33500,0.6242666840553284,0.6242667280435562,4.271653074741364,, 34000,0.7392385601997375,0.7392385556697846,4.156681216239929,, 34500,0.6858959794044495,0.685896109700203,4.210023651123047,, 35000,0.7741008996963501,0.7741006736755371,4.12181912279129,, 35000,,,,4.278964817523956,0.6169548630714417 35500,0.6878940463066101,0.6878939098119736,4.208025881290435,, 36000,0.8035808205604553,0.803580673456192,4.092339104652405,, 36500,0.7113879919052124,0.711387946009636,4.184531846046448,, 37000,0.7963433265686035,0.7963431433439255,4.099576655387878,, 37500,0.6648488640785217,0.66484892141819,4.231070861339569,, 38000,0.7154068946838379,0.7154068673849105,4.180512924671173,, 38500,0.7366675138473511,0.7366676189899445,4.159252171516418,, 39000,0.7283844351768494,0.7283845633268357,4.167535279750824,, 39500,0.6823236346244812,0.68232364320755,4.213596140861511,, 40000,0.7168934941291809,0.7168934712409973,4.179026353359222,, 40000,,,,4.189265376329422,0.7066543102264404 40500,0.7949668765068054,0.794966873049736,4.1009529242515566,, 41000,0.6693404316902161,0.6693403062820434,4.226579475402832,, 41500,0.6857988238334656,0.6857988123893738,4.210120984077454,, 42000,0.755073070526123,0.7550731259584427,4.140846685886383,, 42500,0.8175814747810364,0.8175814466476441,4.078338354587555,, 43000,0.7839120626449585,0.7839119883775711,4.112007808685303,, 43500,0.7063608765602112,0.7063609124422073,4.189558895587921,, 44000,0.7658085227012634,0.7658086522817612,4.130111127853394,, 44500,0.7486372590065002,0.748637336730957,4.147282459259033,, 45000,0.7885012626647949,0.7885013158321381,4.1074184827804565,, 45000,,,,4.274430186748504,0.6214895248413086 45500,0.7435002326965332,0.7435002250671386,4.152419579982758,, 46000,0.7639614343643188,0.7639614179134369,4.131958381652832,, 46500,0.8107367753982544,0.8107365908622741,4.08518321275711,, 47000,0.8047438859939575,0.8047438862323761,4.091175891876221,, 47500,0.6921923160552979,0.6921921135187149,4.2037276868820195,, 48000,0.7561903595924377,0.7561902544498443,4.139729523658753,, 48500,0.7898547649383545,0.7898545687198639,4.106065253734589,, 49000,0.7473968863487244,0.7473968962430954,4.148522877693177,, 49500,0.7425698041915894,0.7425697010755539,4.153350086212158,, 50000,0.7734639048576355,0.7734638048410416,4.122456010818482,, 50000,,,,4.376912138462067,0.5190076231956482