| step,training/mean_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward | |
| 500,-1.2948715686798096,8.537464655399322,, | |
| 1000,-1.2602366209030151,8.502829139232636,, | |
| 1500,-1.2590324878692627,8.501623792648315,, | |
| 2000,-1.303997278213501,8.54658932352066,, | |
| 2500,-1.2511717081069946,8.493763326644897,, | |
| 3000,-1.3589394092559814,8.60153074979782,, | |
| 3500,-1.2393139600753784,8.48190557384491,, | |
| 4000,-1.2551265954971313,8.49771831035614,, | |
| 4500,-1.2294862270355225,8.472077757358552,, | |
| 5000,-1.2666794061660767,8.509271525859832,, | |
| 5000,,,7.966637665033341,-0.7240458071231842 | |
| 5500,-1.2642416954040527,8.506834322929382,, | |
| 6000,-1.3328057527542114,8.57539730644226,, | |
| 6500,-1.2501471042633057,8.492738009929656,, | |
| 7000,-1.2666990756988525,8.509291419029235,, | |
| 7500,-1.2748128175735474,8.517405213356017,, | |
| 8000,-1.2740546464920044,8.516646611690522,, | |
| 8500,-1.2052034139633179,8.447795090198516,, | |
| 9000,-1.182864785194397,8.425456734657288,, | |
| 9500,-1.2884403467178345,8.5310315823555,, | |
| 10000,-1.233523964881897,8.476115854263305,, | |
| 10000,,,7.9207673525810245,-0.6781754946708679 | |
| 10500,-1.2627235651016235,8.505315338134766,, | |
| 11000,-1.2311738729476929,8.473765755176544,, | |
| 11500,-1.2263537645339966,8.468946398735046,, | |
| 12000,-1.1317873001098633,8.374379018306731,, | |
| 12500,-1.1669551134109497,8.409547520399094,, | |
| 13000,-1.1718875169754028,8.41447982287407,, | |
| 13500,-1.1702485084533691,8.412841398715972,, | |
| 14000,-1.1646369695663452,8.40722866153717,, | |
| 14500,-1.2230224609375,8.465613629341126,, | |
| 15000,-1.1647130250930786,8.40730525970459,, | |
| 15000,,,7.9565617620944975,-0.7139699041843415 | |
| 15500,-1.1504708528518677,8.393062113761902,, | |
| 16000,-1.124070167541504,8.366661835670472,, | |
| 16500,-1.1938308477401733,8.436422379970551,, | |
| 17000,-1.1334937810897827,8.37608543729782,, | |
| 17500,-1.1346924304962158,8.377284130573273,, | |
| 18000,-1.231303334236145,8.473895420074463,, | |
| 18500,-1.1544829607009888,8.397074615478516,, | |
| 19000,-1.1664668321609497,8.40905849313736,, | |
| 19500,-1.0910210609436035,8.333612595081329,, | |
| 20000,-1.116986870765686,8.359578641414643,, | |
| 20000,,,7.865157885551453,-0.6225660276412964 | |
| 20500,-1.196850299835205,8.43944271659851,, | |
| 21000,-1.1666178703308105,8.40921020412445,, | |
| 21500,-1.0362211465835571,8.278812587738036,, | |
| 22000,-1.0936347246170044,8.33622686433792,, | |
| 22500,-1.123854160308838,8.366445979118348,, | |
| 23000,-1.1502525806427002,8.392844843864442,, | |
| 23500,-1.048585057258606,8.291176141738891,, | |
| 24000,-1.0508968830108643,8.293488435745239,, | |
| 24500,-1.0698078870773315,8.312400405883789,, | |
| 25000,-1.0558797121047974,8.298471341609956,, | |
| 25000,,,7.896991009712219,-0.654399151802063 | |
| 25500,-1.0177298784255981,8.260322118759156,, | |
| 26000,-1.1420350074768066,8.384627064228058,, | |
| 26500,-1.0078272819519043,8.25041923570633,, | |
| 27000,-0.9816940426826477,8.224285922527313,, | |
| 27500,-1.0749205350875854,8.317512173652648,, | |
| 28000,-1.0614173412322998,8.304009720802307,, | |
| 28500,-1.0408825874328613,8.283474720478058,, | |
| 29000,-1.0226104259490967,8.265202493667603,, | |
| 29500,-1.0688477754592896,8.311439654827119,, | |
| 30000,-1.0776655673980713,8.320257207870483,, | |
| 30000,,,7.928358175754547,-0.6857663178443909 | |
| 30500,-1.0996885299682617,8.342280438899994,, | |
| 31000,-1.0431692600250244,8.28576131439209,, | |
| 31500,-0.9323897361755371,8.174981526374816,, | |
| 32000,-1.0448123216629028,8.287404282569884,, | |
| 32500,-1.0457897186279297,8.28838144350052,, | |
| 33000,-0.9990127682685852,8.241604254245757,, | |
| 33500,-1.0288316011428833,8.271423215389252,, | |
| 34000,-0.9391740560531616,8.181765538215638,, | |
| 34500,-0.9481043219566345,8.190695775985718,, | |
| 35000,-0.9675369262695312,8.210128994464874,, | |
| 35000,,,7.7664533042907715,-0.5238614463806153 | |
| 35500,-0.9987792372703552,8.241371144294739,, | |
| 36000,-1.0705009698867798,8.31309298992157,, | |
| 36500,-0.9814274311065674,8.22401949262619,, | |
| 37000,-1.0326741933822632,8.275266448736192,, | |
| 37500,-0.9649855494499207,8.207577040672302,, | |
| 38000,-0.9077735543251038,8.15036545228958,, | |
| 38500,-0.8409937620162964,8.083585484981537,, | |
| 39000,-0.8864595890045166,8.129051558971405,, | |
| 39500,-0.9210060834884644,8.163597695827484,, | |
| 40000,-0.9630925059318542,8.20568466424942,, | |
| 40000,,,7.686182173490525,-0.44359031558036804 | |
| 40500,-0.9604359269142151,8.20302740097046,, | |
| 41000,-0.9391587972640991,8.18175057554245,, | |
| 41500,-0.8852586150169373,8.127850399494172,, | |
| 42000,-1.0065287351608276,8.249120641708375,, | |
| 42500,-0.9923439621925354,8.234935368537903,, | |
| 43000,-0.8635305762290955,8.106122595310211,, | |
| 43500,-0.9286391735076904,8.171230719566346,, | |
| 44000,-0.9256390333175659,8.168231150627136,, | |
| 44500,-0.8891777396202087,8.131769494056702,, | |
| 45000,-0.9140955209732056,8.156687272071839,, | |
| 45000,,,7.693421269655228,-0.4508294117450714 | |
| 45500,-0.8853515386581421,8.127943280696869,, | |
| 46000,-0.8782824277877808,8.120874377250672,, | |
| 46500,-0.9314770698547363,8.174069253921509,, | |
| 47000,-0.9545345902442932,8.197126769542693,, | |
| 47500,-0.7800334095954895,8.022625288963319,, | |
| 48000,-0.9076521396636963,8.150243569850922,, | |
| 48500,-0.8409892320632935,8.08358046245575,, | |
| 49000,-0.7971982359886169,8.039790264606475,, | |
| 49500,-0.879081130027771,8.121672852516173,, | |
| 50000,-0.8535681962966919,8.096159941673278,, | |
| 50000,,,7.607669181823731,-0.3650773239135742 | |
| 50500,-0.7938743829727173,8.036466488838196,, | |
| 51000,-0.8821865916252136,8.124778107643127,, | |