step,training/mean_reward,training/mean_global_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward 500,0.07416050136089325,0.07416052532196045,4.820838501930237,, 1000,0.3993367850780487,0.39933697843551635,4.495662048816681,, 1500,0.641542911529541,0.6415428266525268,4.25345620059967,, 2000,0.6912615299224854,0.6912616682052612,4.2037373590469365,, 2500,0.8411300778388977,0.8411300249099731,4.053869002342224,, 3000,0.66389399766922,0.6638941321372985,4.231104895114899,, 3500,0.5875337719917297,0.5875337800979614,4.307465247154235,, 4000,0.5281067490577698,0.528106767654419,4.366892259597778,, 4500,0.617109477519989,0.6171096386909485,4.277889388561249,, 5000,0.5186097025871277,0.5186096467971801,4.376389380455017,, 5000,,,,4.388545849323273,0.5064530968666077 5500,0.8105007410049438,0.810500518321991,4.084498508930206,, 6000,0.9420019388198853,0.9420019421577454,3.952997085094452,, 6500,0.627610981464386,0.6276109175682067,4.26738810968399,, 7000,0.6816001534461975,0.6816003184318542,4.213398708820343,, 7500,0.5582146644592285,0.5582146592140198,4.3367843680381775,, 8000,0.7186452150344849,0.7186452231407165,4.17635380411148,, 8500,0.8303737044334412,0.8303737545013428,4.064625272750854,, 9000,0.9805426597595215,0.9805426783561707,3.9144563488960267,, 9500,0.9399061799049377,0.9399062571525574,3.95509277009964,, 10000,0.8024645447731018,0.8024646391868592,4.092534388065338,, 10000,,,,4.166729226112365,0.7282697558403015 10500,0.7322391867637634,0.7322392110824585,4.162759816169738,, 11000,0.792961835861206,0.7929619455337524,4.102037081718445,, 11500,0.7022609114646912,0.7022608528137207,4.192738174438476,, 12000,0.8131945729255676,0.813194571018219,4.081804456233979,, 12500,0.7196359038352966,0.7196359448432922,4.175363082408905,, 13000,0.8793307542800903,0.8793307743072509,4.015668252944947,, 13500,0.8689985275268555,0.8689985194206238,4.026000507831574,, 14000,0.8344987630844116,0.8344986805915833,4.060500346660614,, 14500,0.6935732960700989,0.6935730800628662,4.201425947189331,, 15000,0.8293156027793884,0.8293154816627503,4.065683545589447,, 15000,,,,4.199550375938416,0.6954484581947327 15500,0.847747802734375,0.8477478699684143,4.047251157283783,, 16000,0.8586597442626953,0.8586595516204834,4.0363394756317135,, 16500,0.7595199346542358,0.7595198173522949,4.135479209899902,, 17000,0.7075164318084717,0.7075164089202881,4.187482618331909,, 17500,0.8406838774681091,0.8406837244033813,4.054315302848816,, 18000,0.832733690738678,0.8327336320877076,4.06226539516449,, 18500,0.8194519877433777,0.8194520301818847,4.075546997070313,, 19000,0.7307292819023132,0.7307292885780334,4.164269738674164,, 19500,0.7931746244430542,0.793174665927887,4.101824361324311,, 20000,0.7238526940345764,0.7238528842926025,4.171146142959595,, 20000,,,,4.149334579706192,0.7456643581390381 20500,0.8676466941833496,0.8676466164588928,4.027352410793305,, 21000,0.7644018530845642,0.7644017372131348,4.130597290039063,, 21500,0.8096491694450378,0.8096491394042968,4.0853498878479,, 22000,0.8646054863929749,0.864605438709259,4.030393588542938,, 22500,0.8054022789001465,0.8054019861221313,4.089597041130066,, 23000,0.7088119983673096,0.7088119959831238,4.186187031269074,, 23500,0.8164091110229492,0.816409080028534,4.078589947223663,, 24000,0.6761070489883423,0.6761069912910461,4.218892035961151,, 24500,0.8275026679039001,0.8275024971961975,4.067496530055999,, 25000,0.8072778582572937,0.8072777452468872,4.08772128200531,, 25000,,,,4.3447775602340695,0.5502213835716248 25500,0.738605260848999,0.7386052641868591,4.1563937630653385,, 26000,0.7604418396949768,0.7604417572021485,4.134557270050049,, 26500,0.6931183338165283,0.6931184191703796,4.201880608081818,, 27000,0.8136337995529175,0.8136338605880737,4.081365166664123,, 27500,0.779967725276947,0.7799677534103393,4.115031273841858,, 28000,0.7684062719345093,0.7684062099456788,4.126592817306519,, 28500,0.8337153196334839,0.8337151594161988,4.061283867835998,, 29000,0.8212065696716309,0.8212065019607544,4.073792525291443,, 29500,0.7639384269714355,0.7639382700920105,4.131060757160187,, 30000,0.7043402791023254,0.704340184211731,4.190658843040466,, 30000,,,,4.368393664360046,0.5266052484512329 30500,0.8462768197059631,0.8462766733169556,4.048722353935242,, 31000,0.8047793507575989,0.8047793531417846,4.090219674110412,, 31500,0.9042069911956787,0.9042068982124328,3.9907921290397645,, 32000,0.7123118042945862,0.712311933517456,4.182687093734741,, 32500,0.7604222893714905,0.760422125339508,4.1345769019126895,, 33000,0.7690596580505371,0.7690595760345459,4.1259394512176515,, 33500,0.5666108131408691,0.5666108646392822,4.3283881626129155,, 34000,0.7384089231491089,0.7384088406562805,4.156590186595917,, 34500,0.7680999040603638,0.7680997700691223,4.126899257183075,, 35000,0.6674128770828247,0.6674129161834716,4.227586111068725,, 35000,,,,4.59938203215599,0.29561686515808105 35500,0.7690004110336304,0.769000367641449,4.125998659610748,, 36000,0.7767564058303833,0.7767563238143921,4.118242703437805,, 36500,0.6897526383399963,0.6897524900436401,4.2052465372085575,, 37000,0.7634567022323608,0.7634567775726319,4.1315422496795655,, 37500,0.9539850354194641,0.9539852085113525,3.9410138187408448,, 38000,0.6920108199119568,0.6920106902122497,4.2029883370399475,, 38500,0.8514260053634644,0.8514259538650513,4.0435730733871456,, 39000,0.7491832971572876,0.7491833515167237,4.145815675735474,, 39500,0.7215076088905334,0.7215076670646667,4.173491360187531,, 40000,0.8197861313819885,0.8197861957550049,4.0752128314971925,, 40000,,,,4.279830825328827,0.6151681542396545 40500,0.7313529849052429,0.7313528170585633,4.163646210193634,, 41000,0.6913750171661377,0.6913750095367431,4.2036240177154545,, 41500,0.7348246574401855,0.73482461643219,4.160174410820007,, 42000,0.8678916096687317,0.8678916101455688,4.027107417106628,, 42500,0.8538818359375,0.8538821640014649,4.041116863250733,, 43000,0.8073235750198364,0.8073236093521118,4.087675417900085,, 43500,0.873058021068573,0.8730578751564025,4.021941152095795,, 44000,0.7564084529876709,0.7564084305763245,4.138590596675873,, 44500,0.7083547115325928,0.7083547067642212,4.186644320487976,, 45000,0.8611916899681091,0.8611917090415955,4.033807318210602,, 45000,,,,4.525386850833893,0.3696120083332062 45500,0.8180867433547974,0.8180867652893067,4.076912261962891,, 46000,0.6938366889953613,0.6938366603851318,4.201162366867066,, 46500,0.7701635956764221,0.7701636538505554,4.124835373401642,, 47000,0.8981485962867737,0.8981486325263977,3.9968503947257994,, 47500,0.7367319464683533,0.7367320342063903,4.158266993045807,, 48000,0.8405490517616272,0.8405489931106568,4.05445003414154,, 48500,0.8713409900665283,0.8713407883644104,4.023658238887787,, 49000,0.6517473459243774,0.6517471113204956,4.243251915931702,, 49500,0.8187721967697144,0.8187721009254456,4.076226926326751,, 50000,0.7222646474838257,0.722264636516571,4.172734390735626,, 50000,,,,4.521365547180176,0.37363338470458984