step,training/mean_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward 500,-0.05469633638858795,4.950616147994995,, 1000,-0.020106935873627663,4.916026740074158,, 1500,-0.07065746933221817,4.966577284812927,, 2000,-0.03580048307776451,4.931720273971558,, 2500,-0.03538388013839722,4.931303685188293,, 3000,-0.004608032293617725,4.90052783203125,, 3500,0.0015521363820880651,4.894367663383484,, 4000,-0.0010029735276475549,4.896922773361206,, 4500,0.02290673367679119,4.873013066291809,, 5000,0.017220541834831238,4.87869926071167,, 5000,,,4.74536141872406,0.15055838108062744 5500,0.035649269819259644,4.860270520210266,, 6000,0.054371125996112823,4.841548697471619,, 6500,0.07879267632961273,4.817127106666565,, 7000,0.08227484673261642,4.813644940376282,, 7500,0.0698215588927269,4.826098240852356,, 8000,0.11395218968391418,4.781967616081237,, 8500,0.1522676646709442,4.743652131080627,, 9000,0.34084072709083557,4.555079117298126,, 9500,0.2056790143251419,4.690240668296814,, 10000,0.2790547311306,4.616865202426911,, 10000,,,4.322903940677643,0.5730158591270447 10500,0.4393679201602936,4.456551766872406,, 11000,0.3624029755592346,4.533516850948334,, 11500,0.45795243978500366,4.437967555522919,, 12000,0.5219399929046631,4.373979769229889,, 12500,0.5190432071685791,4.3768767361640935,, 13000,0.5514355301856995,4.344484226703644,, 13500,0.5568577647209167,4.339061886787414,, 14000,0.6298843622207642,4.266035663127899,, 14500,0.5918717980384827,4.30404780960083,, 15000,0.5902144312858582,4.305705562114715,, 15000,,,4.234160472154617,0.6617593276500702 15500,0.5965772867202759,4.299343195438385,, 16000,0.5926651358604431,4.303254592895508,, 16500,0.6194234490394592,4.276496342658996,, 17000,0.6140950918197632,4.281824736595154,, 17500,0.601017415523529,4.294902472496033,, 18000,0.6147196888923645,4.28119990825653,, 18500,0.6663503646850586,4.229569540977478,, 19000,0.6542154550552368,4.241704180240631,, 19500,0.6863803267478943,4.209539662837982,, 20000,0.6043404340744019,4.2915796327590945,, 20000,,,4.441113437414169,0.4548063623905182 20500,0.5835577845573425,4.312361845493316,, 21000,0.60400390625,4.291915914058685,, 21500,0.5713146328926086,4.324605407238007,, 22000,0.6183692812919617,4.277550545692444,, 22500,0.651496171951294,4.244423900604248,, 23000,0.6971624493598938,4.198757387638092,, 23500,0.7256056666374207,4.170314098834991,, 24000,0.7674533128738403,4.128466490268707,, 24500,0.6783409714698792,4.217579075336456,, 25000,0.7554478645324707,4.140471652030945,, 25000,,,4.1483421385288235,0.7475776612758637 25500,0.664194643497467,4.231725151062012,, 26000,0.7436407804489136,4.1522788887023925,, 26500,0.6402836441993713,4.2556358814239506,, 27000,0.704365611076355,4.191554109573365,, 27500,0.6806281805038452,4.215291363716125,, 28000,0.7311782240867615,4.164741626262665,, 28500,0.668502151966095,4.227417692184448,, 29000,0.7228501439094543,4.173069821834564,, 29500,0.6775731444358826,4.21834666633606,, 30000,0.709757387638092,4.18616290140152,, 30000,,,4.185533491373062,0.7103863084316253 30500,0.7017973065376282,4.194122500896454,, 31000,0.7023854851722717,4.193534404277801,, 31500,0.6915497183799744,4.204369942188263,, 32000,0.6947381496429443,4.201181643486023,, 32500,0.7347754836082458,4.161144144058228,, 33000,0.715140163898468,4.1807798237800595,, 33500,0.6970503926277161,4.198869513988495,, 34000,0.7122536301612854,4.18366656255722,, 34500,0.6721194386482239,4.223800676822663,, 35000,0.7084102034568787,4.1875097680091855,, 35000,,,4.064277943372726,0.8316418564319611 35500,0.7381153106689453,4.157804275512695,, 36000,0.7371877431869507,4.158732101917267,, 36500,0.7305323481559753,4.165387609481812,, 37000,0.7102790474891663,4.185640233993531,, 37500,0.7457661032676697,4.1501536011695865,, 38000,0.8023549914360046,4.093564716815949,, 38500,0.7496578097343445,4.146262320041656,, 39000,0.7447620034217834,4.15115793800354,, 39500,0.685832142829895,4.210087802886963,, 40000,0.7611342668533325,4.134785517692566,, 40000,,,4.055977816581726,0.8399419832229614 40500,0.7217703461647034,4.1741497139930726,, 41000,0.7378434538841248,4.158076527118683,, 41500,0.7570021748542786,4.138917275905609,, 42000,0.7797091007232666,4.116210601806641,, 42500,0.7915752530097961,4.104344500541687,, 43000,0.7516778111457825,4.144241992950439,, 43500,0.7928832173347473,4.1030366277694705,, 44000,0.7899062633514404,4.106013395786285,, 44500,0.797512948513031,4.098406736373901,, 45000,0.7636102437973022,4.132309415340424,, 45000,,,3.955502781867981,0.9404170179367065 45500,0.729123055934906,4.166796465873718,, 46000,0.7812316417694092,4.114688412189484,, 46500,0.7331199049949646,4.162799956798554,, 47000,0.7391576766967773,4.156762266635895,, 47500,0.8011806011199951,4.094739077091217,, 48000,0.7617540955543518,4.13416605758667,, 48500,0.7448456287384033,4.151074337005615,, 49000,0.8135129809379578,4.082406508922577,, 49500,0.7758315205574036,4.120088108539582,, 50000,0.766567587852478,4.129351999759674,, 50000,,,4.237590322494507,0.6583294773101807