| step,training/mean_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward | |
| 500,-0.8125036954879761,7.241255680084229,, | |
| 1000,-0.7975343465805054,7.2262860627174375,, | |
| 1500,-0.7210679650306702,7.149820563316346,, | |
| 2000,-0.7730409502983093,7.201792915821075,, | |
| 2500,-0.7463775277137756,7.175129210948944,, | |
| 3000,-0.7051370143890381,7.133889080047608,, | |
| 3500,-0.7185169458389282,7.147268382072449,, | |
| 4000,-0.7259790897369385,7.154731070518493,, | |
| 4500,-0.6839227080345154,7.112674701690674,, | |
| 5000,-0.683942973613739,7.112694909095764,, | |
| 5000,,,6.803549926280976,-0.37479798078536986 | |
| 5500,-0.6878058314323425,7.116558263778686,, | |
| 6000,-0.5987275242805481,7.027479179382325,, | |
| 6500,-0.5734506249427795,7.002202389717102,, | |
| 7000,-0.5246564745903015,6.953408542633056,, | |
| 7500,-0.5056997537612915,6.9344518222808835,, | |
| 8000,-0.4681713879108429,6.896923281669617,, | |
| 8500,-0.4946156442165375,6.923367538928986,, | |
| 9000,-0.4399287700653076,6.868680774688721,, | |
| 9500,-0.34558820724487305,6.774340056419373,, | |
| 10000,-0.19040487706661224,6.61915679693222,, | |
| 10000,,,6.31689129114151,0.11186065435409547 | |
| 10500,-0.12325085699558258,6.5520028295516965,, | |
| 11000,-0.017721027135849,6.446473007678986,, | |
| 11500,-0.12777179479599,6.556523683071137,, | |
| 12000,-0.023241819813847542,6.451993795394897,, | |
| 12500,-0.04334178566932678,6.4720937218666075,, | |
| 13000,-0.03740231320261955,6.466154263019562,, | |
| 13500,-0.014202435500919819,6.442954377651215,, | |
| 14000,-0.00828587356954813,6.437037821769715,, | |
| 14500,0.007885211147367954,6.420866765022278,, | |
| 15000,0.02104600891470909,6.407705917358398,, | |
| 15000,,,6.388269504308701,0.04048244118690491 | |
| 15500,0.19436894357204437,6.23438299703598,, | |
| 16000,0.1590561419725418,6.269695870399475,, | |
| 16500,0.13854582607746124,6.2902060608863835,, | |
| 17000,0.1756041944026947,6.253147789955139,, | |
| 17500,0.2104174941778183,6.218334442138672,, | |
| 18000,0.48283150792121887,5.945920520305633,, | |
| 18500,0.27904483675956726,6.149707182407379,, | |
| 19000,0.5020908713340759,5.926660984516144,, | |
| 19500,0.2641090452671051,6.164642835140229,, | |
| 20000,0.31925344467163086,6.1094984126091,, | |
| 20000,,,6.503148951530457,-0.07439700603485107 | |
| 20500,0.6079156398773193,5.820836288452148,, | |
| 21000,0.6040365099906921,5.824715541839599,, | |
| 21500,0.2768762707710266,6.151875576019287,, | |
| 22000,0.2680024802684784,6.160749494552612,, | |
| 22500,0.18345756828784943,6.24529434633255,, | |
| 23000,0.3401566445827484,6.088595186710358,, | |
| 23500,0.5622674822807312,5.866484387874603,, | |
| 24000,0.5155385136604309,5.913213373184204,, | |
| 24500,0.11084838956594467,6.317903567790985,, | |
| 25000,0.4057731628417969,6.022978693008423,, | |
| 25000,,,6.407343668937683,0.021408276557922365 | |
| 25500,0.39409419894218445,6.0346575789451595,, | |
| 26000,0.5344062447547913,5.894345436573029,, | |
| 26500,0.3507353961467743,6.0780166525840755,, | |
| 27000,0.3328927755355835,6.0958592348098755,, | |
| 27500,0.2797487676143646,6.149003215789795,, | |
| 28000,0.5223521590232849,5.906399938106537,, | |
| 28500,0.30235573649406433,6.126395907402038,, | |
| 29000,0.5017824769020081,5.9269694204330445,, | |
| 29500,0.49171748757362366,5.9370342926979065,, | |
| 30000,0.47422295808792114,5.954529101371765,, | |
| 30000,,,6.438512723445893,-0.009760777950286865 | |
| 30500,0.3593529760837555,6.0693990015983585,, | |
| 31000,0.6325029134750366,5.796249008655548,, | |
| 31500,0.5082643628120422,5.920487454414368,, | |
| 32000,0.305186003446579,6.123565795421601,, | |
| 32500,0.6483381986618042,5.7804135632514955,, | |
| 33000,0.5877586007118225,5.8409933109283445,, | |
| 33500,0.5236616730690002,5.905090319633484,, | |
| 34000,0.6374344825744629,5.791317390441894,, | |
| 34500,0.1322925090789795,6.296459455966949,, | |
| 35000,0.6908378005027771,5.737914066314698,, | |
| 35000,,,5.849234503507614,0.5795174419879914 | |
| 35500,0.5664113163948059,5.862340573310852,, | |
| 36000,0.582101047039032,5.846650831699371,, | |
| 36500,0.5723392367362976,5.856412885189056,, | |
| 37000,0.6953791379928589,5.7333726620674135,, | |
| 37500,0.6672109365463257,5.76154154586792,, | |
| 38000,0.7148140072822571,5.713938286781311,, | |
| 38500,0.6594667434692383,5.769285338401795,, | |
| 39000,0.7301754951477051,5.698576348304749,, | |
| 39500,0.6522349119186401,5.776516912937164,, | |
| 40000,0.6596822738647461,5.769069487571716,, | |
| 40000,,,5.566042425632477,0.8627095198631287 | |
| 40500,0.7279464602470398,5.70080558681488,, | |
| 41000,0.5207101106643677,5.9080419330596925,, | |
| 41500,0.5918683409690857,5.83688342666626,, | |
| 42000,0.7508755326271057,5.677876295089722,, | |
| 42500,0.7545020580291748,5.674249963760376,, | |
| 43000,0.7839584350585938,5.644793807029724,, | |
| 43500,0.5337421298027039,5.895009816646576,, | |
| 44000,0.7882859110832214,5.640466244697571,, | |
| 44500,0.5786499381065369,5.850102061271667,, | |
| 45000,0.813514232635498,5.615237611293793,, | |
| 45000,,,5.568185291290283,0.8605666542053223 | |
| 45500,0.6137551069259644,5.814997109413147,, | |
| 46000,0.7409204840660095,5.687831499576569,, | |
| 46500,0.7055236101150513,5.7232285490036015,, | |
| 47000,0.830437421798706,5.598314429283142,, | |
| 47500,0.4375966191291809,5.991155071258545,, | |
| 48000,0.7365174889564514,5.6922339172363285,, | |
| 48500,0.5435031652450562,5.885248740196228,, | |
| 49000,0.6381453275680542,5.79060683631897,, | |
| 49500,0.6407182216644287,5.788033958911896,, | |
| 50000,0.6731566190719604,5.755595561981202,, | |
| 50000,,,5.68962007522583,0.7391318702697753 | |