step,training/mean_reward,training/mean_global_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward 500,0.1211983934044838,0.12119838809967041,2.3229451456069947,, 1000,0.31621789932250977,0.3162178590297699,2.127925674676895,, 1500,0.27846118807792664,0.2784611864089966,2.1656823472976683,, 2000,0.38813117146492004,0.388131156206131,2.056012377500534,, 2500,0.4311320185661316,0.4311320331096649,2.013011500597,, 3000,0.42855799198150635,0.42855797219276426,2.015585561513901,, 3500,0.4381873905658722,0.43818740773200987,2.005956125974655,, 4000,0.4550243318080902,0.45502435183525086,1.9891191818714142,, 4500,0.4636005163192749,0.46360058736801146,1.9805429463386535,, 5000,0.4499755799770355,0.4499756269454956,1.9941679067611695,, 5000,,,,1.9980125480890274,0.44613099098205566 5500,0.4342297315597534,0.4342297592163086,2.0099137744903564,, 6000,0.43782952427864075,0.43782948184013365,2.0063140518665312,, 6500,0.4488549530506134,0.4488549630641937,1.9952885706424712,, 7000,0.46629998087882996,0.4663000383377075,1.9778434953689574,, 7500,0.4562501013278961,0.4562501287460327,1.9878934049606323,, 8000,0.4785791337490082,0.47857914090156556,1.9655643928050994,, 8500,0.46689385175704956,0.4668938534259796,1.9772496802806854,, 9000,0.46674633026123047,0.4667463300228119,1.9773972036838532,, 9500,0.450894832611084,0.4508948402404785,1.9932486934661866,, 10000,0.46775224804878235,0.4677522621154785,1.9763912715911864,, 10000,,,,2.0244746845960617,0.41966885328292847 10500,0.4305729568004608,0.43057299494743345,2.0135705387592315,, 11000,0.4356262683868408,0.4356263179779053,2.0085172157287596,, 11500,0.4279658794403076,0.42796586036682127,2.0161776733398438,, 12000,0.4394981265068054,0.4394981548786163,2.0046453788280485,, 12500,0.42419159412384033,0.4241916081905365,2.0199519255161285,, 13000,0.4269791543483734,0.42697916793823243,2.0171643657684326,, 13500,0.4085043668746948,0.40850441336631776,2.035639120340347,, 14000,0.43079009652137756,0.4307900664806366,2.0133534672260285,, 14500,0.41863885521888733,0.4186388657093048,2.0255046679973603,, 15000,0.4017929136753082,0.4017929284572601,2.0423506052494047,, 15000,,,,2.0018797904253005,0.44226372241973877 15500,0.4049068093299866,0.4049067852497101,2.039236748456955,, 16000,0.40300869941711426,0.40300868701934817,2.0411348466873167,, 16500,0.36362409591674805,0.36362405586242674,2.080519477844238,, 17000,0.3969660997390747,0.3969660987854004,2.047177434921265,, 17500,0.3620345890522003,0.36203460812568666,2.0821089255809784,, 18000,0.3918434977531433,0.3918435068130493,2.0523000268936156,, 18500,0.37731635570526123,0.37731636977195737,2.0668271639347076,, 19000,0.3512536287307739,0.3512536237239838,2.092889909982681,, 19500,0.42915791273117065,0.4291579520702362,2.014985581636429,, 20000,0.43425044417381287,0.4342504734992981,2.009893060207367,, 20000,,,,2.006538985967636,0.43760454654693604 20500,0.4370073974132538,0.4370074245929718,2.0071361091136932,, 21000,0.39508068561553955,0.3950807240009308,2.049062809705734,, 21500,0.3991532623767853,0.39915324091911314,2.044990292787552,, 22000,0.41835564374923706,0.41835569667816164,2.0257878370285036,, 22500,0.40474262833595276,0.40474259638786314,2.039400937318802,, 23000,0.4015122652053833,0.4015122666358948,2.0426312670707705,, 23500,0.40508830547332764,0.4050883343219757,2.0390551993846895,, 24000,0.3816099762916565,0.38160997080802916,2.062533562898636,, 24500,0.3659219443798065,0.3659219119548798,2.0782216217517853,, 25000,0.38788846135139465,0.38788845348358153,2.0562550802230835,, 25000,,,,2.0386839401721955,0.40545961260795593 25500,0.400818407535553,0.40081840109825134,2.043325132608414,, 26000,0.40071311593055725,0.4007131004333496,2.0434304332733153,, 26500,0.39686304330825806,0.3968630077838898,2.0472805259227753,, 27000,0.37206801772117615,0.3720680310726166,2.0720755026340485,, 27500,0.3768540024757385,0.3768539924621582,2.0672895412445067,, 28000,0.3948107361793518,0.3948107616901398,2.049332772016525,, 28500,0.39682313799858093,0.3968231508731842,2.047320382833481,, 29000,0.4006522297859192,0.4006522183418274,2.0434913153648377,, 29500,0.40053775906562805,0.4005377535820007,2.0436057801246643,, 30000,0.40711328387260437,0.40711328196525576,2.037030251741409,, 30000,,,,1.9804821747541428,0.4636613130569458 30500,0.4391063153743744,0.43910632872581484,2.0050372049808503,, 31000,0.4444220960140228,0.44442206382751465,1.9997214698791503,, 31500,0.4572528600692749,0.4572528700828552,1.9868906636238097,, 32000,0.45334821939468384,0.4533482458591461,1.990795287847519,, 32500,0.4223582148551941,0.42235823011398316,2.021785303592682,, 33000,0.4451010823249817,0.4451010935306549,1.99904244017601,, 33500,0.46457594633102417,0.46457596611976626,1.979567567586899,, 34000,0.45398586988449097,0.45398587012290953,1.9901576635837555,, 34500,0.44113367795944214,0.4411336877346039,2.0030098459720613,, 35000,0.4434558153152466,0.44345577478408815,2.000687758922577,, 35000,,,,1.972090377807617,0.4720531105995178 35500,0.448396235704422,0.448396232843399,1.995747300863266,, 36000,0.4446418583393097,0.4446418530941009,1.999501680612564,, 36500,0.46207195520401,0.46207195520401,1.982071578502655,, 37000,0.4563034772872925,0.45630345726013183,1.9878400764465332,, 37500,0.4596448838710785,0.45964489483833315,1.9844986388683319,, 38000,0.4605804979801178,0.4605805559158325,1.9835629777908326,, 38500,0.4548853039741516,0.45488534355163573,1.9892581901550292,, 39000,0.4458518624305725,0.4458518526554108,1.9982916810512543,, 39500,0.4311184287071228,0.43111842036247255,2.0130251133441925,, 40000,0.41672754287719727,0.4167275586128235,2.0274159750938416,, 40000,,,,2.0608232545852663,0.38332027196884155 40500,0.42195016145706177,0.42195015454292295,2.022193379163742,, 41000,0.4213549494743347,0.4213549509048462,2.022788582801819,, 41500,0.432466059923172,0.4324660618305206,2.0116774718761445,, 42000,0.43227460980415344,0.43227460360527037,2.011868930101395,, 42500,0.4086211025714874,0.40862109684944153,2.0355224368572236,, 43000,0.4045468270778656,0.40454684138298036,2.0395966923236846,, 43500,0.4512312412261963,0.45123124623298644,1.9929122874736787,, 44000,0.4639366567134857,0.46393660593032837,1.9802069277763368,, 44500,0.4432682693004608,0.4432682845592499,2.0008752491474153,, 45000,0.46199217438697815,0.46199217581748964,1.9821513578891754,, 45000,,,,1.984584556221962,0.45955896377563477 45500,0.43364131450653076,0.4336413471698761,2.010502186536789,, 46000,0.42340052127838135,0.4234005537033081,2.020742980003357,, 46500,0.4161236882209778,0.41612367415428164,2.0280198595523835,, 47000,0.41465526819229126,0.41465527772903443,2.029488255977631,, 47500,0.40847858786582947,0.40847854590415955,2.0356649878025057,, 48000,0.4093286693096161,0.4093286414146423,2.034814892292023,, 48500,0.4342298209667206,0.4342298080921173,2.0099137256145476,, 49000,0.4297516345977783,0.4297516813278198,2.014391852378845,, 49500,0.4133729934692383,0.41337298560142516,2.03077054810524,, 50000,0.3909572660923004,0.3909572880268097,2.0531862456798553,, 50000,,,,2.045583736896515,0.3985597491264343