step,training/mean_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward 500,-0.8859584331512451,7.314710327625274,, 1000,-0.8464276790618896,7.275179624557495,, 1500,-0.873164713382721,7.301917225837707,, 2000,-0.8966192007064819,7.325370721817016,, 2500,-0.8892086744308472,7.317960293769836,, 3000,-0.8551289439201355,7.283881196022033,, 3500,-0.8791598081588745,7.307911730289459,, 4000,-0.9048333764076233,7.333585097312927,, 4500,-0.8619924187660217,7.290744475364685,, 5000,-0.7942509651184082,7.22300271987915,, 5000,,,6.944387233257293,-0.5156352877616882 5500,-0.8535743355751038,7.282326291084289,, 6000,-0.8811347484588623,7.309886821746826,, 6500,-0.8881641030311584,7.316915870189667,, 7000,-0.8647947311401367,7.293546379566193,, 7500,-0.855954647064209,7.284707161426544,, 8000,-0.7725940346717834,7.201346005439758,, 8500,-0.8203192353248596,7.2490712475776675,, 9000,-0.7990893125534058,7.227841438293457,, 9500,-0.8235146999359131,7.2522663335800175,, 10000,-0.8104425668716431,7.23919427061081,, 10000,,,6.915240397453308,-0.48648845195770263 10500,-0.7764639258384705,7.205215943336487,, 11000,-0.7666837573051453,7.19543618440628,, 11500,-0.7238384485244751,7.152590212345124,, 12000,-0.7413204312324524,7.170072130203247,, 12500,-0.7593003511428833,7.188052515983582,, 13000,-0.7714426517486572,7.200194663047791,, 13500,-0.7454770803451538,7.174228974342347,, 14000,-0.774897038936615,7.203648768424988,, 14500,-0.7788583040237427,7.207610322475434,, 15000,-0.7019731402397156,7.130724880695343,, 15000,,,6.815973980426788,-0.38722203493118285 15500,-0.7183502912521362,7.1471022615432735,, 16000,-0.7278227210044861,7.156574978351593,, 16500,-0.6718280911445618,7.100580026626587,, 17000,-0.7033256888389587,7.132077807426453,, 17500,-0.653221607208252,7.081973798274994,, 18000,-0.635442316532135,7.064193972110749,, 18500,-0.7247795462608337,7.153531385421753,, 19000,-0.6652644276618958,7.094016726016998,, 19500,-0.661221444606781,7.089973773002624,, 20000,-0.6771378517150879,7.1058895592689515,, 20000,,,6.7617291378974915,-0.332977192401886 20500,-0.7235527634620667,7.152304513454437,, 21000,-0.6785742044448853,7.107325972557068,, 21500,-0.6812253594398499,7.109977578639984,, 22000,-0.5582377910614014,6.986990109443664,, 22500,-0.6299605369567871,7.058712802886963,, 23000,-0.5498843193054199,6.978636440753937,, 23500,-0.5934484601020813,7.022200397014618,, 24000,-0.595256507396698,7.024008573532105,, 24500,-0.5555814504623413,6.98433303976059,, 25000,-0.5683977603912354,6.997149734020233,, 25000,,,6.720896201133728,-0.2921442556381226 25500,-0.5259677767753601,6.954720021724701,, 26000,-0.5571457743644714,6.985897304534912,, 26500,-0.593763530254364,7.022515581130982,, 27000,-0.5692958235740662,6.998047782897949,, 27500,-0.5378536581993103,6.966605662345886,, 28000,-0.6279689073562622,7.056720701217651,, 28500,-0.5946992635726929,7.023451109409332,, 29000,-0.57447350025177,7.0032253818511965,, 29500,-0.4391641616821289,6.867916213035583,, 30000,-0.51848965883255,6.947241683006286,, 30000,,,6.595395767688752,-0.16664382219314575 30500,-0.5157312154769897,6.944482862472534,, 31000,-0.466669499874115,6.895421423912048,, 31500,-0.46547091007232666,6.894222658157348,, 32000,-0.5000770688056946,6.92882893371582,, 32500,-0.5261947512626648,6.954946808338165,, 33000,-0.45057910680770874,6.879331085681915,, 33500,-0.44003963470458984,6.8687914099693295,, 34000,-0.4788571298122406,6.907609120845795,, 34500,-0.4767308831214905,6.905482939720153,, 35000,-0.49058422446250916,6.919335837364197,, 35000,,,6.564518105983734,-0.13576616048812867 35500,-0.4219120740890503,6.850663848876954,, 36000,-0.38950878381729126,6.818260639667511,, 36500,-0.4359693229198456,6.864721201896668,, 37000,-0.37029531598091125,6.799047232627869,, 37500,-0.4194263815879822,6.848178487300872,, 38000,-0.40659159421920776,6.835343776702881,, 38500,-0.3782537877559662,6.807005780696869,, 39000,-0.42156270146369934,6.850314499855042,, 39500,-0.4140963852405548,6.842848338127136,, 40000,-0.40227124094963074,6.831023153305054,, 40000,,,6.47081268787384,-0.042060742378234865 40500,-0.36971181631088257,6.798463690757751,, 41000,-0.43966588377952576,6.868417775154113,, 41500,-0.3883586525917053,6.8171105122566225,, 42000,-0.3849063515663147,6.813657989025116,, 42500,-0.358828604221344,6.787580660820007,, 43000,-0.3558928966522217,6.784644738674164,, 43500,-0.33561772108078003,6.76436952161789,, 44000,-0.3434455096721649,6.7721971940994266,, 44500,-0.38202962279319763,6.810781738758087,, 45000,-0.34480559825897217,6.7735575685501095,, 45000,,,6.378945187330246,0.049806758165359497 45500,-0.2776198983192444,6.706371777534485,, 46000,-0.21592065691947937,6.644672675132751,, 46500,-0.42913031578063965,6.857882392883301,, 47000,-0.3731894791126251,6.801941444396973,, 47500,-0.2851388454437256,6.713890775680542,, 48000,-0.2749994695186615,6.703751484870911,, 48500,-0.3163752257823944,6.745127034187317,, 49000,-0.29249221086502075,6.721244281291962,, 49500,-0.28145650029182434,6.710208463668823,, 50000,-0.3123234212398529,6.741075382709504,, 50000,,,6.350747134685516,0.07800481081008911 50500,-0.26684442162513733,6.69559634065628,, 51000,-0.2741592526435852,6.702911217212677,,