step,training/mean_reward,training/mean_global_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward 500,0.07879238575696945,0.07879239296913147,2.3653511407375336,, 1000,0.3019788861274719,0.3019788889884949,2.14216464471817,, 1500,0.3008267283439636,0.3008266839981079,2.1433168497085573,, 2000,0.321493923664093,0.3214939081668854,2.1226496255397795,, 2500,0.317903608083725,0.3179036159515381,2.126239917755127,, 3000,0.3061528205871582,0.30615282368659974,2.1379907100200652,, 3500,0.3353806138038635,0.3353806071281433,2.108762926578522,, 4000,0.2867070436477661,0.28670704007148745,2.1574364936351778,, 4500,0.3438643217086792,0.3438643124103546,2.1002792212963106,, 5000,0.3053115904331207,0.30531160545349123,2.138831928253174,, 5000,,,,2.1970818293094636,0.24706171452999115 5500,0.3116154074668884,0.31161540174484254,2.1325281319618226,, 6000,0.27000534534454346,0.27000535917282104,2.174138174533844,, 6500,0.322913259267807,0.32291331005096435,2.121230223655701,, 7000,0.31720975041389465,0.317209743976593,2.126933789730072,, 7500,0.3562520742416382,0.3562520523071289,2.087891481399536,, 8000,0.35564085841178894,0.35564088487625123,2.088502648830414,, 8500,0.37320002913475037,0.37320003247261047,2.0709435012340545,, 9000,0.39041516184806824,0.3904151809215546,2.0537283527851105,, 9500,0.36799564957618713,0.3679956450462341,2.0761478886604308,, 10000,0.3698658347129822,0.36986583733558653,2.0742776963710785,, 10000,,,,2.0536168885231016,0.3905266523361206 10500,0.38033413887023926,0.3803341522216797,2.0638093814849854,, 11000,0.3552154004573822,0.35521537280082705,2.088928160905838,, 11500,0.34528854489326477,0.34528851985931397,2.098855013847351,, 12000,0.3219221830368042,0.321922189950943,2.1222213437557222,, 12500,0.3171769380569458,0.3171769230365753,2.1269666106700895,, 13000,0.2982843220233917,0.29828434228897094,2.145859191417694,, 13500,0.29687371850013733,0.29687372875213625,2.147269804954529,, 14000,0.28632494807243347,0.28632496285438536,2.1578185708522795,, 14500,0.29477766156196594,0.29477765727043154,2.1493658764362333,, 15000,0.2864285409450531,0.2864285111427307,2.1577150225639343,, 15000,,,,2.14560660302639,0.29853689670562744 15500,0.300083726644516,0.30008373761177065,2.1440597960948944,, 16000,0.275886595249176,0.27588662767410277,2.1682569060325623,, 16500,0.27856478095054626,0.2785647757053375,2.1655787580013275,, 17000,0.27140673995018005,0.2714067316055298,2.1727368021011353,, 17500,0.26500755548477173,0.2650075664520264,2.1791359672546387,, 18000,0.2250824272632599,0.22508242511749268,2.2190611085891723,, 18500,0.19682329893112183,0.19682328820228576,2.2473202455043793,, 19000,0.18034976720809937,0.18034976935386657,2.2637937643527986,, 19500,0.2258571982383728,0.22585719680786132,2.2182863368988035,, 20000,0.24266906082630157,0.24266906809806824,2.2014744656085967,, 20000,,,,2.0718668192625045,0.3722766935825348 20500,0.3705962598323822,0.3705962131023407,2.0735473206043245,, 21000,0.37643730640411377,0.376437349319458,2.067706184387207,, 21500,0.3848373591899872,0.38483733797073366,2.0593061957359313,, 22000,0.3726760745048523,0.3726761016845703,2.0714674320220947,, 22500,0.396867960691452,0.39686795473098757,2.0472755789756776,, 23000,0.373384028673172,0.37338405418396,2.070759479522705,, 23500,0.3717637360095978,0.3717637438774109,2.072379789829254,, 24000,0.3783749043941498,0.3783749122619629,2.065768621444702,, 24500,0.382399320602417,0.38239933133125303,2.061744202375412,, 25000,0.414162278175354,0.414162303686142,2.029981230020523,, 25000,,,,2.0406938391923903,0.4034497141838074 25500,0.41153985261917114,0.41153987383842466,2.0326036598682404,, 26000,0.3912021517753601,0.3912021427154541,2.052941390991211,, 26500,0.39947420358657837,0.3994742147922516,2.0446693189144134,, 27000,0.4021007716655731,0.4021007769107819,2.042042756795883,, 27500,0.39653480052948,0.39653480195999147,2.047608731746674,, 28000,0.4009231626987457,0.40092321729660035,2.0432203164100646,, 28500,0.37516528367996216,0.37516525077819823,2.068978282928467,, 29000,0.37784603238105774,0.37784601497650144,2.0662975187301638,, 29500,0.3974778354167938,0.3974778389930725,2.0466656947135924,, 30000,0.38078832626342773,0.38078833842277526,2.0633551952838896,, 30000,,,,2.0952959829568862,0.34884750843048096 30500,0.3939836621284485,0.39398367786407473,2.0501598558425904,, 31000,0.39895930886268616,0.3989593091011047,2.0451842246055603,, 31500,0.38997411727905273,0.3899741132259369,2.0541694204807284,, 32000,0.3846270740032196,0.3846270706653595,2.0595164630413056,, 32500,0.3826240003108978,0.38262401914596555,2.0615195145606995,, 33000,0.37986674904823303,0.37986676454544066,2.0642767691612245,, 33500,0.4051167070865631,0.40511670088768004,2.039026832818985,, 34000,0.40417876839637756,0.40417876267433167,2.0399647710323334,, 34500,0.42090508341789246,0.420905074596405,2.02323845911026,, 35000,0.42834019660949707,0.4283402225971222,2.015803311109543,, 35000,,,,2.0259674841165545,0.4181760549545288 35500,0.40599969029426575,0.40599973702430725,2.0381437966823577,, 36000,0.40902745723724365,0.4090274679660797,2.0351160657405853,, 36500,0.4161769449710846,0.4161769680976868,2.0279665656089785,, 37000,0.4008311927318573,0.4008312106132507,2.0433123230934145,, 37500,0.41739287972450256,0.41739288353919984,2.026750650167465,, 38000,0.42290589213371277,0.4229059457778931,2.021237587928772,, 38500,0.4291313588619232,0.4291313602924347,2.0150121734142306,, 39000,0.40294578671455383,0.4029457657337189,2.041197767972946,, 39500,0.40372490882873535,0.4037249138355255,2.0404186198711396,, 40000,0.4180188477039337,0.41801887726783754,2.0261246564388276,, 40000,,,,2.018271576166153,0.42587196826934814 40500,0.41336074471473694,0.41336077857017517,2.0307827551364896,, 41000,0.38819581270217896,0.38819580101966855,2.0559477326869966,, 41500,0.39462125301361084,0.3946212561130524,2.0495222775936126,, 42000,0.36356356739997864,0.3635635905265808,2.0805799431800844,, 42500,0.3919467329978943,0.39194677186012267,2.052196761846542,, 43000,0.4150419533252716,0.41504194688796997,2.0291015868186952,, 43500,0.4383908808231354,0.4383908848762512,2.0057526488304136,, 44000,0.42800629138946533,0.42800630164146425,2.016137232065201,, 44500,0.432797908782959,0.43279793071746825,2.0113456029891967,, 45000,0.4234403967857361,0.4234403958320618,2.0207031378746034,, 45000,,,,1.9671885770559312,0.47695493698120117 45500,0.4703380763530731,0.4703380696773529,1.9738054640293121,, 46000,0.4686366021633148,0.46863656067848203,1.975506973028183,, 46500,0.45165979862213135,0.4516598210334778,1.9924837126731874,, 47000,0.46325457096099854,0.4632545506954193,1.9808889830112457,, 47500,0.47780492901802063,0.4778049213886261,1.9663386123180389,, 48000,0.4450892508029938,0.44508927297592166,1.9990542607307433,, 48500,0.4382834732532501,0.43828349232673647,2.0058600413799286,, 49000,0.4080190062522888,0.4080190143585205,2.0361245193481445,, 49500,0.4382653832435608,0.43826538705825807,2.005878146648407,, 50000,0.4289587736129761,0.4289587852954865,2.0151847484111785,, 50000,,,,2.063185594677925,0.3809579312801361