| step,training/mean_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward |
| 500,-0.8337574601173401,7.2625089368820195,, |
| 1000,-0.8844476938247681,7.313199779033661,, |
| 1500,-0.8568709492683411,7.285622939109802,, |
| 2000,-0.8764241337776184,7.305176173210144,, |
| 2500,-0.8833082318305969,7.3120601658821105,, |
| 3000,-0.843629002571106,7.272381494045257,, |
| 3500,-0.8558563590049744,7.284608540534973,, |
| 4000,-0.897135853767395,7.325887870311737,, |
| 4500,-0.8800743222236633,7.3088264956474305,, |
| 5000,-0.8353054523468018,7.264057570457458,, |
| 5000,,,6.861332287788391,-0.43258034229278564 |
| 5500,-0.8824276328086853,7.311180031299591,, |
| 6000,-0.8075532913208008,7.236305090904236,, |
| 6500,-0.7708455324172974,7.199597449302673,, |
| 7000,-0.8518726229667664,7.280624206542969,, |
| 7500,-0.8252453804016113,7.25399791431427,, |
| 8000,-0.8556382060050964,7.284389909744263,, |
| 8500,-0.8292795419692993,7.258031998634339,, |
| 9000,-0.7825701236724854,7.211322192668915,, |
| 9500,-0.8399323225021362,7.268684284687042,, |
| 10000,-0.8699889779090881,7.298740811347962,, |
| 10000,,,6.7721366119384765,-0.3433846664428711 |
| 10500,-0.7759202718734741,7.204672615528107,, |
| 11000,-0.8226161599159241,7.251367949485779,, |
| 11500,-0.7830278873443604,7.211779610157013,, |
| 12000,-0.7756528854370117,7.204404586315155,, |
| 12500,-0.7357938885688782,7.164546077251434,, |
| 13000,-0.8023674488067627,7.231119527816772,, |
| 13500,-0.8034653067588806,7.232217133522034,, |
| 14000,-0.809131920337677,7.237883892536163,, |
| 14500,-0.7554364204406738,7.184188369274139,, |
| 15000,-0.6900954246520996,7.118847215652466,, |
| 15000,,,6.71194739818573,-0.2831954526901245 |
| 15500,-0.7772068381309509,7.205958922863006,, |
| 16000,-0.7398184537887573,7.16857056427002,, |
| 16500,-0.7340170741081238,7.162769122123718,, |
| 17000,-0.7754262089729309,7.204178487300873,, |
| 17500,-0.6328316330909729,7.061583570480346,, |
| 18000,-0.6913192272186279,7.12007083272934,, |
| 18500,-0.7261297106742859,7.1548818597793575,, |
| 19000,-0.7182119488716125,7.146963843822479,, |
| 19500,-0.6714723706245422,7.1002243523597715,, |
| 20000,-0.7200285196304321,7.148780225753784,, |
| 20000,,,6.634492812156677,-0.20574086666107178 |
| 20500,-0.6988351345062256,7.127586895942688,, |
| 21000,-0.5833439230918884,7.012095543861389,, |
| 21500,-0.7299511432647705,7.158702974796295,, |
| 22000,-0.6898444890975952,7.118596746444702,, |
| 22500,-0.6177433729171753,7.046495225429535,, |
| 23000,-0.647895336151123,7.0766476283073425,, |
| 23500,-0.5564975738525391,6.9852493720054625,, |
| 24000,-0.6292154788970947,7.057967645168304,, |
| 24500,-0.6698049902915955,7.098556845664978,, |
| 25000,-0.6355842351913452,7.064336626529694,, |
| 25000,,,6.570861332416534,-0.14210938692092895 |
| 25500,-0.6185728907585144,7.047324940681458,, |
| 26000,-0.5699464082717896,6.998698216438293,, |
| 26500,-0.510445237159729,6.939197426319122,, |
| 27000,-0.6018198728561401,7.03057196521759,, |
| 27500,-0.6035413146018982,7.032293075561523,, |
| 28000,-0.584702730178833,7.013454456329345,, |
| 28500,-0.5893553495407104,7.018107319831848,, |
| 29000,-0.619099497795105,7.047851248264313,, |
| 29500,-0.5167713165283203,6.945523273944855,, |
| 30000,-0.5577331781387329,6.986484991073608,, |
| 30000,,,6.480864057540893,-0.05211211204528809 |
| 30500,-0.5592696070671082,6.9880216026306154,, |
| 31000,-0.5265080332756042,6.955260110855103,, |
| 31500,-0.47589394450187683,6.904645955085754,, |
| 32000,-0.4596564471721649,6.888408284664154,, |
| 32500,-0.5010589361190796,6.929811083316803,, |
| 33000,-0.5123630166053772,6.941114960670471,, |
| 33500,-0.4425766170024872,6.871328568935394,, |
| 34000,-0.4919807016849518,6.92073282289505,, |
| 34500,-0.6038171648979187,7.032568644046783,, |
| 35000,-0.596716046333313,7.02546796798706,, |
| 35000,,,6.414432802200317,0.014319143295288085 |
| 35500,-0.45767953991889954,6.88643150806427,, |
| 36000,-0.48255276679992676,6.911304312705994,, |
| 36500,-0.456580251455307,6.885332314014435,, |
| 37000,-0.4541272819042206,6.882879360675812,, |
| 37500,-0.3991451859474182,6.827896891117096,, |
| 38000,-0.45182034373283386,6.88057210969925,, |
| 38500,-0.4978872537612915,6.926639170646667,, |
| 39000,-0.4291215240955353,6.857873545169831,, |
| 39500,-0.44742172956466675,6.8761735091209415,, |
| 40000,-0.3595379590988159,6.7882899899482725,, |
| 40000,,,6.451553264856338,-0.02280131936073303 |
| 40500,-0.37442320585250854,6.803175215244293,, |
| 41000,-0.4653773009777069,6.894129150867462,, |
| 41500,-0.3763178288936615,6.805069895267486,, |
| 42000,-0.4605293273925781,6.889281231880188,, |
| 42500,-0.398901104927063,6.82765292263031,, |
| 43000,-0.3718828856945038,6.800634912490844,, |
| 43500,-0.35147905349731445,6.780230886936188,, |
| 44000,-0.3776282072067261,6.8063800616264345,, |
| 44500,-0.3661980628967285,6.794949872016907,, |
| 45000,-0.4164592921733856,6.845211396217346,, |
| 45000,,,6.34353432059288,0.08521762490272522 |
| 45500,-0.42424657940864563,6.852998693943023,, |
| 46000,-0.3722217082977295,6.800973816871643,, |
| 46500,-0.3386153280735016,6.767367269039154,, |
| 47000,-0.45362889766693115,6.882381087303162,, |
| 47500,-0.34361785650253296,6.772369818687439,, |
| 48000,-0.3325020372867584,6.761253938674927,, |
| 48500,-0.35177308320999146,6.780524806976318,, |
| 49000,-0.3360912501811981,6.764843159198761,, |
| 49500,-0.24793630838394165,6.676688256263733,, |
| 50000,-0.3225588798522949,6.751310648918152,, |
| 50000,,,6.311479724645615,0.11727222084999084 |
| 50500,-0.3060561418533325,6.734807965278626,, |
| 51000,-0.24912001192569733,6.677872049331665,, |
|
|