| step,training/mean_reward,training/mean_global_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward | |
| 500,-0.05419518053531647,-0.05419515490531921,4.950114953994751,, | |
| 1000,-0.09147597849369049,-0.09147588479518891,4.987395686149597,, | |
| 1500,-0.08628850430250168,-0.08628857612609864,4.982208367824555,, | |
| 2000,-0.0665811151266098,-0.0665812623500824,4.962501091003418,, | |
| 2500,-0.035610511898994446,-0.03561058747768402,4.931530386924743,, | |
| 3000,-0.01836210861802101,-0.01836207091808319,4.914281900405884,, | |
| 3500,-0.023731190711259842,-0.023731261253356933,4.919651072502136,, | |
| 4000,-0.052384521812200546,-0.05238448619842529,4.948304272651672,, | |
| 4500,0.024747055023908615,0.024746983885765076,4.871172795295715,, | |
| 5000,0.026996605098247528,0.026996595740318298,4.868923198223114,, | |
| 5000,,,,4.74390513420105,0.15201453864574432 | |
| 5500,0.05313940718770027,0.05313949406147003,4.842780306339264,, | |
| 6000,0.029855646193027496,0.029855628967285157,4.866064166069031,, | |
| 6500,0.09584029018878937,0.095840212225914,4.800079608917236,, | |
| 7000,0.07065510749816895,0.07065506303310394,4.825264736175537,, | |
| 7500,0.08642834424972534,0.08642830944061279,4.809491467475891,, | |
| 8000,0.0908430889248848,0.09084308755397796,4.805076703071594,, | |
| 8500,0.1055099293589592,0.10551000726222992,4.790409780979156,, | |
| 9000,0.14785964787006378,0.1478595850467682,4.748060173034668,, | |
| 9500,0.12757433950901031,0.12757443964481355,4.768345353603363,, | |
| 10000,0.12898088991641998,0.12898102939128875,4.766938761234283,, | |
| 10000,,,,4.637168612480163,0.2587510645389557 | |
| 10500,0.12769140303134918,0.12769152808189393,4.768228325366974,, | |
| 11000,0.11455798149108887,0.11455799865722656,4.781361808776856,, | |
| 11500,0.09204788506031036,0.09204791736602783,4.803871840476989,, | |
| 12000,0.12754663825035095,0.12754654788970948,4.768373266220093,, | |
| 12500,0.10625479370355606,0.10625489008426667,4.7896649041175845,, | |
| 13000,0.1600775569677353,0.16007758772373198,4.735842207908631,, | |
| 13500,0.16082805395126343,0.16082817530632018,4.7350916056633,, | |
| 14000,0.14281372725963593,0.14281375312805175,4.753106033325195,, | |
| 14500,0.1921832412481308,0.1921832768917084,4.703736530303955,, | |
| 15000,0.19292289018630981,0.19292283248901368,4.702996956348419,, | |
| 15000,,,,4.498863337039947,0.3970564305782318 | |
| 15500,0.22589251399040222,0.2258924732208252,4.670027330398559,, | |
| 16000,0.21598325669765472,0.21598324084281922,4.679936559677124,, | |
| 16500,0.22806762158870697,0.22806767416000367,4.66785213470459,, | |
| 17000,0.23223277926445007,0.23223274719715117,4.663687035560608,, | |
| 17500,0.25238272547721863,0.2523827393054962,4.643537058353424,, | |
| 18000,0.22750389575958252,0.2275037943124771,4.668415998935699,, | |
| 18500,0.2678506076335907,0.26785062098503115,4.628069185256958,, | |
| 19000,0.23563972115516663,0.23563972628116608,4.660280067443848,, | |
| 19500,0.24484607577323914,0.2448459883928299,4.651073840141296,, | |
| 20000,0.2511804699897766,0.2511805219650269,4.644739252567291,, | |
| 20000,,,,4.3774751496315005,0.5184444189071655 | |
| 20500,0.22951728105545044,0.22951722717285156,4.666402591228485,, | |
| 21000,0.2973259687423706,0.29732601630687716,4.598593772888184,, | |
| 21500,0.2796284258365631,0.27962837982177735,4.616291418552398,, | |
| 22000,0.28537634015083313,0.2853763234615326,4.610543473720551,, | |
| 22500,0.2773391902446747,0.27733917140960695,4.618580641746521,, | |
| 23000,0.2961649000644684,0.2961648225784302,4.599754945755005,, | |
| 23500,0.2988382875919342,0.29883816647529604,4.597081629276276,, | |
| 24000,0.2936323583126068,0.2936324553489685,4.602287340641022,, | |
| 24500,0.3022133708000183,0.3022134164571762,4.593706405639648,, | |
| 25000,0.3116600513458252,0.3116598607301712,4.584259963989258,, | |
| 25000,,,,4.200006374120712,0.6959133744239807 | |
| 25500,0.36219388246536255,0.36219400668144225,4.533725776195526,, | |
| 26000,0.337605357170105,0.33760546004772185,4.558314349174499,, | |
| 26500,0.33722004294395447,0.3372200413942337,4.558699756622315,, | |
| 27000,0.34060221910476685,0.3406023781299591,4.555317396640778,, | |
| 27500,0.3580511808395386,0.3580512089729309,4.537868612766266,, | |
| 28000,0.3830181956291199,0.3830182863473892,4.512901507377625,, | |
| 28500,0.3455016314983368,0.3455015660524368,4.550418251991272,, | |
| 29000,0.3419179916381836,0.3419180706739426,4.554001727581024,, | |
| 29500,0.3621671199798584,0.36216720950603487,4.533752601623535,, | |
| 30000,0.3638201057910919,0.3638200658559799,4.5320997266769405,, | |
| 30000,,,,4.177131632566452,0.7187880873680115 | |
| 30500,0.37916675209999084,0.3791667002439499,4.516753098487854,, | |
| 31000,0.37497958540916443,0.3749796770811081,4.520940135955811,, | |
| 31500,0.4327625334262848,0.4327624168395996,4.463157413482666,, | |
| 32000,0.3613492250442505,0.3613490802049637,4.53457070016861,, | |
| 32500,0.3923645317554474,0.39236452782154085,4.5035552611351015,, | |
| 33000,0.3820577561855316,0.38205777704715727,4.513862028121948,, | |
| 33500,0.4104272723197937,0.41042733764648437,4.485492463588715,, | |
| 34000,0.38328781723976135,0.38328776705265044,4.512632042884826,, | |
| 34500,0.40013033151626587,0.4001304520368576,4.495789341449737,, | |
| 35000,0.40230631828308105,0.402306361913681,4.49361342716217,, | |
| 35000,,,,4.1181962931156155,0.7777233719825745 | |
| 35500,0.410239040851593,0.41023910415172576,4.485680697441101,, | |
| 36000,0.43223410844802856,0.4322340644598007,4.463685748100281,, | |
| 36500,0.4221329391002655,0.42213293516635897,4.473786841869354,, | |
| 37000,0.4262062609195709,0.4262062772512436,4.4697135076522825,, | |
| 37500,0.4071034789085388,0.40710352969169616,4.488816298484802,, | |
| 38000,0.46916699409484863,0.46916701483726503,4.4267527933120725,, | |
| 38500,0.4102042317390442,0.41020408749580384,4.485715694904328,, | |
| 39000,0.4500734508037567,0.45007349145412445,4.4458463001251225,, | |
| 39500,0.3865085244178772,0.38650842976570127,4.509411367893219,, | |
| 40000,0.4345833659172058,0.4345834237337112,4.461336367130279,, | |
| 40000,,,,4.168105397224426,0.727814257144928 | |
| 40500,0.3862174451351166,0.3862172917127609,4.5097025203704835,, | |
| 41000,0.40553659200668335,0.40553656208515165,4.490383221626281,, | |
| 41500,0.45195287466049194,0.45195285725593565,4.443966904163361,, | |
| 42000,0.4800412356853485,0.48004123866558074,4.4158785552978514,, | |
| 42500,0.4769391715526581,0.47693934237957003,4.418980459213257,, | |
| 43000,0.4732610881328583,0.47326107835769654,4.422658719539642,, | |
| 43500,0.4636530876159668,0.46365314626693727,4.432266639709472,, | |
| 44000,0.4664022624492645,0.46640234375,4.429517439842224,, | |
| 44500,0.48438000679016113,0.48438021051883695,4.411539603233337,, | |
| 45000,0.5152715444564819,0.5152714885473252,4.380648320198059,, | |
| 45000,,,,4.124990088939667,0.7709295749664307 | |
| 45500,0.5066302418708801,0.5066303426027298,4.389289425849914,, | |
| 46000,0.48212766647338867,0.482127604842186,4.413792192935944,, | |
| 46500,0.501164436340332,0.5011644350290299,4.394755397319794,, | |
| 47000,0.5257378816604614,0.5257379056215287,4.370181900024414,, | |
| 47500,0.45488241314888,0.4548824690580368,4.441037350654602,, | |
| 48000,0.5186976790428162,0.5186976329088211,4.377222174167633,, | |
| 48500,0.4871944189071655,0.48719434118270877,4.408725499629974,, | |
| 49000,0.4708578288555145,0.47085785269737246,4.425061961650848,, | |
| 49500,0.5483450293540955,0.5483450331687927,4.347574764251709,, | |
| 50000,0.5446288585662842,0.5446287850141526,4.3512910113334655,, | |
| 50000,,,,4.086982932090759,0.8089367747306824 | |