step,training/mean_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward 500,-0.06781058758497238,4.9637303524017335,, 1000,-0.023672502487897873,4.919592318534851,, 1500,-0.07853193581104279,4.974451763153076,, 2000,-0.035383231937885284,4.931303065299987,, 2500,-0.03465710207819939,4.930576898574829,, 3000,0.005867821630090475,4.89005197763443,, 3500,0.013212079182267189,4.882707726478577,, 4000,0.008638734929263592,4.8872810649871825,, 4500,0.007477673701941967,4.888442126274109,, 5000,0.009070250205695629,4.886849549293518,, 5000,,,4.791192696094513,0.10472710371017456 5500,0.024794861674308777,4.871124946594239,, 6000,0.05810078978538513,4.837819006919861,, 6500,0.04036615043878555,4.8555536527633665,, 7000,0.07348232716321945,4.822437491416931,, 7500,0.07930152863264084,4.816618280410767,, 8000,0.031271710991859436,4.8646480884552,, 8500,0.0978122428059578,4.798107528686524,, 9000,0.12935470044612885,4.76656510257721,, 9500,0.17599347233772278,4.719926267623902,, 10000,0.30185937881469727,4.594060430526733,, 10000,,,4.535047419071198,0.36087238073349 10500,0.2173570990562439,4.67856263589859,, 11000,0.36601805686950684,4.529901868820191,, 11500,0.4207775592803955,4.475142490386963,, 12000,0.46978995203971863,4.426129657745362,, 12500,0.4339540898799896,4.46196563577652,, 13000,0.4531416893005371,4.442778135299682,, 13500,0.5287524461746216,4.367167568206787,, 14000,0.6296225786209106,4.266297729969025,, 14500,0.6073395013809204,4.288580012321472,, 15000,0.6502442955970764,4.245675333499909,, 15000,,,4.078059881925583,0.8178599178791046 15500,0.6094864010810852,4.286433386325836,, 16000,0.576747715473175,4.31917227935791,, 16500,0.5418465733528137,4.35407312297821,, 17000,0.6178687810897827,4.278051248073578,, 17500,0.570162296295166,4.32575726556778,, 18000,0.748081386089325,4.147837859153747,, 18500,0.7194918394088745,4.176427851676941,, 19000,0.767803966999054,4.128115781307221,, 19500,0.7078751921653748,4.188044494152069,, 20000,0.6302920579910278,4.26562738609314,, 20000,,,4.28806955575943,0.6078502440452576 20500,0.6465226411819458,4.249396784305572,, 21000,0.624789834022522,4.271129950523377,, 21500,0.5421141386032104,4.3538054451942445,, 22000,0.5155944228172302,4.380325298309327,, 22500,0.5910283327102661,4.304891526222229,, 23000,0.7030788660049438,4.192841132640838,, 23500,0.6312992572784424,4.264620572090149,, 24000,0.7310395836830139,4.164880690574646,, 24500,0.7469294667243958,4.148990183830262,, 25000,0.7668827772140503,4.12903725862503,, 25000,,,4.1328072929382325,0.763112506866455 25500,0.7234245538711548,4.172495340824127,, 26000,0.8244341611862183,4.071485727310181,, 26500,0.7321522831916809,4.1637675976753235,, 27000,0.8058591485023499,4.090060839653015,, 27500,0.7332265973091125,4.162693355083466,, 28000,0.8214840888977051,4.074435817241668,, 28500,0.7634644508361816,4.132455599784851,, 29000,0.8121892809867859,4.083731027126312,, 29500,0.8029031753540039,4.093016468048096,, 30000,0.8253943920135498,4.070525625705719,, 30000,,,4.047812665700913,0.848107134103775 30500,0.8176087141036987,4.078310852050781,, 31000,0.859913170337677,4.036006732463837,, 31500,0.7579036951065063,4.1380158362388615,, 32000,0.721142053604126,4.1747777094841005,, 32500,0.7813311815261841,4.114588516712189,, 33000,0.9146214127540588,3.981298336029053,, 33500,0.7316060066223145,4.164313527584076,, 34000,0.8223187327384949,4.073601455211639,, 34500,0.7863075137138367,4.109611881732941,, 35000,0.8018606305122375,4.094058545589447,, 35000,,,4.052333083152771,0.8435867166519165 35500,0.7866441607475281,4.109275463581085,, 36000,0.6843576431274414,4.211561968803406,, 36500,0.7851774096488953,4.110742897510528,, 37000,0.7223367094993591,4.173582774162292,, 37500,0.7794983983039856,4.116421010494232,, 38000,0.8302304744720459,4.065689761161805,, 38500,0.9220008254051208,3.9739190998077394,, 39000,0.7866688966751099,4.109250622272492,, 39500,0.7502818703651428,4.145638114452362,, 40000,0.845702588558197,4.0502174415588375,, 40000,,,4.103545006513595,0.792374793291092 40500,0.7982372045516968,4.097682444572449,, 41000,0.9099467992782593,3.985972822189331,, 41500,0.9163407683372498,3.9795794448852537,, 42000,0.8405916690826416,4.055328216552734,, 42500,0.6296499967575073,4.266269786834717,, 43000,0.7018924355506897,4.194027076721191,, 43500,0.8460696339607239,4.049849932193756,, 44000,0.9300314784049988,3.965888786792755,, 44500,0.7789812684059143,4.116938692569732,, 45000,0.8481354117393494,4.047784205913544,, 45000,,,4.156538715362549,0.7393810844421387 45500,0.7278191447257996,4.168100543022156,, 46000,0.808249294757843,4.087670279502869,, 46500,0.7946467399597168,4.101273151874542,, 47000,0.8370266556739807,4.058892886638642,, 47500,0.7812142968177795,4.114705813884735,, 48000,0.823106586933136,4.072812892436981,, 48500,0.8241832852363586,4.07173668050766,, 49000,0.8589930534362793,4.036926683425904,, 49500,0.8229879140853882,4.07293142080307,, 50000,0.8775739669799805,4.018345596313477,, 50000,,,4.060356808900833,0.8355629909038543