step,training/mean_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward 500,-0.06010052189230919,4.956020358085632,, 1000,-0.06762798130512238,4.963547794342041,, 1500,-0.010410509072244167,4.9063303089141845,, 2000,-0.024178912863135338,4.920098714828491,, 2500,-0.01725992187857628,4.913179714202881,, 3000,0.007104979362338781,4.888814820289612,, 3500,-0.0194217711687088,4.915341593742371,, 4000,-0.0017699870513752103,4.897689786911011,, 4500,-0.03245826065540314,4.928378060340881,, 5000,0.01641271635890007,4.879507085800171,, 5000,,,4.768201396465302,0.127718403339386 5500,0.029624976217746735,4.866294813156128,, 6000,0.016804752871394157,4.879115047931671,, 6500,0.060361843556165695,4.835557951927185,, 7000,0.0506209135055542,4.845298888206482,, 7500,0.10555047541856766,4.790369305610657,, 8000,0.13636621832847595,4.7595536336898805,, 8500,0.14338061213493347,4.752539157867432,, 9000,0.11938703805208206,4.776532757759094,, 9500,0.188872292637825,4.7070475254058834,, 10000,0.18474562466144562,4.711174118995666,, 10000,,,4.276217106580734,0.6197026932239532 10500,0.24091115593910217,4.655008587837219,, 11000,0.35235732793807983,4.543562410831451,, 11500,0.44227170944213867,4.453648137569427,, 12000,0.4837493896484375,4.412170240402221,, 12500,0.5292168855667114,4.3667029809951785,, 13000,0.5780242681503296,4.317895310401917,, 13500,0.544098973274231,4.351820888996124,, 14000,0.5467525720596313,4.3491673679351806,, 14500,0.5458378195762634,4.350081850528717,, 15000,0.5736566185951233,4.322263331413269,, 15000,,,4.2715960574150085,0.6243237423896789 15500,0.49921390414237976,4.396705749034882,, 16000,0.6092562675476074,4.286663562297821,, 16500,0.5513033270835876,4.344616313457489,, 17000,0.6134932041168213,4.282426589488983,, 17500,0.5430799722671509,4.3528400182724,, 18000,0.593995213508606,4.30192418050766,, 18500,0.49793216586112976,4.39798774766922,, 19000,0.5883476734161377,4.30757257270813,, 19500,0.5904688239097595,4.305451178073883,, 20000,0.673524796962738,4.222394959449768,, 20000,,,4.297975962162018,0.5979438376426697 20500,0.7285947799682617,4.167324848175049,, 21000,0.7812251448631287,4.1146949253082274,, 21500,0.6721459031105042,4.223774185180664,, 22000,0.6895936727523804,4.206326550960541,, 22500,0.6798408627510071,4.216079057216644,, 23000,0.6681675314903259,4.2277524929046635,, 23500,0.7090982794761658,4.186821770191193,, 24000,0.7451890110969543,4.150730483531952,, 24500,0.6983412504196167,4.197578183174134,, 25000,0.8501180410385132,4.045801553726196,, 25000,,,4.224447625875473,0.6714721739292144 25500,0.8014905452728271,4.094429267883301,, 26000,0.7351145148277283,4.160805347919464,, 26500,0.7761022448539734,4.119817725658416,, 27000,0.7664259076118469,4.129493451118469,, 27500,0.7401525974273682,4.155767142772675,, 28000,0.836887538433075,4.059032101631164,, 28500,0.8105483651161194,4.085371603488922,, 29000,0.6928315162658691,4.203087983131408,, 29500,0.7837188839912415,4.1122009806632995,, 30000,0.9004902243614197,3.995428780555725,, 30000,,,4.254592294692993,0.6413275051116943 30500,0.8077627420425415,4.088157354831695,, 31000,0.720850944519043,4.17506868648529,, 31500,0.9146949052810669,3.9812251353263854,, 32000,0.8832377195358276,4.012682279109955,, 32500,0.835914671421051,4.060005143642425,, 33000,0.9196045398712158,3.976315257549286,, 33500,0.9254862666130066,3.970433331489563,, 34000,0.7716565132141113,4.12426304769516,, 34500,0.8700727820396423,4.02584788942337,, 35000,0.9270522594451904,3.968867311954498,, 35000,,,3.9585508096218107,0.9373689901828766 35500,0.855806827545166,4.04011278295517,, 36000,0.8928802013397217,4.003039710521698,, 36500,0.8415313959121704,4.054388465404511,, 37000,0.8161708116531372,4.079749258041382,, 37500,0.8102002143859863,4.085719204902649,, 38000,0.8735489845275879,4.022370812892913,, 38500,0.8594521284103394,4.036467477798462,, 39000,0.923952579498291,3.971967272758484,, 39500,0.8303558826446533,4.065563850879669,, 40000,0.8814589381217957,4.01446125125885,, 40000,,,3.865206067562103,1.0307137322425843 40500,0.8280853033065796,4.067834432601929,, 41000,0.8330550789833069,4.062864763736725,, 41500,0.7666528224945068,4.129266968727112,, 42000,0.7516821622848511,4.1442376298904415,, 42500,0.8802570104598999,4.015662420272827,, 43000,0.7664872407913208,4.129432399272918,, 43500,0.8490495681762695,4.046870242595673,, 44000,0.8660760521888733,4.029843455314636,, 44500,0.7808338403701782,4.115085937976837,, 45000,0.8536191582679749,4.0423010053634645,, 45000,,,3.956695319414139,0.9392244803905487 45500,0.8096204400062561,4.086299792766571,, 46000,0.8291450142860413,4.066774940013885,, 46500,0.8081926107406616,4.087727133274078,, 47000,0.7679374814033508,4.127981873989105,, 47500,0.5772661566734314,4.318653561115265,, 48000,0.6518995761871338,4.244020341873169,, 48500,0.8557542562484741,4.040165956020355,, 49000,0.8486754298210144,4.047243885993957,, 49500,0.7023369669914246,4.193582893848419,, 50000,0.8517650365829468,4.044154629707337,, 50000,,,4.131519224643707,0.7644005751609803