step,training/mean_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward 500,-0.8399013876914978,7.268653218269348,, 1000,-0.8453505039215088,7.274102281093597,, 1500,-0.8944687843322754,7.323220608711242,, 2000,-0.8966999053955078,7.325451781272888,, 2500,-0.8439417481422424,7.2726939311027525,, 3000,-0.8640217781066895,7.292773539066315,, 3500,-0.8658046126365662,7.294556648254394,, 4000,-0.8504090309143066,7.279160638809204,, 4500,-0.8361682295799255,7.264919965744019,, 5000,-0.8198047280311584,7.248556134223938,, 5000,,,6.927585701942444,-0.49883375644683836 5500,-0.8693844676017761,7.29813617515564,, 6000,-0.8302263617515564,7.258978052139282,, 6500,-0.882265567779541,7.311017146587372,, 7000,-0.8450828194618225,7.273834724903106,, 7500,-0.8210588693618774,7.249810044765472,, 8000,-0.864189624786377,7.2929416284561155,, 8500,-0.8288588523864746,7.257610685348511,, 9000,-0.8814749121665955,7.310227005004883,, 9500,-0.8095128536224365,7.2382649841308595,, 10000,-0.8696774840354919,7.298429715156555,, 10000,,,7.001179609298706,-0.5724276638031006 10500,-0.7672430276870728,7.195995120048523,, 11000,-0.7678922414779663,7.196644094467163,, 11500,-0.7684344053268433,7.197186339855194,, 12000,-0.7794303297996521,7.2081822481155395,, 12500,-0.9099723100662231,7.338724256038666,, 13000,-0.7771443724632263,7.205896562099457,, 13500,-0.7525932192802429,7.181345272541046,, 14000,-0.7289289236068726,7.157681355953216,, 14500,-0.6601957082748413,7.088947270393372,, 15000,-0.7125511765480042,7.141303400993348,, 15000,,,6.757227876186371,-0.32847593069076536 15500,-0.7023719549179077,7.131124230384827,, 16000,-0.7676927447319031,7.196444457530975,, 16500,-0.6635507345199585,7.092302770614624,, 17000,-0.7325724959373474,7.161323986053467,, 17500,-0.7069200277328491,7.135671969413758,, 18000,-0.7303782105445862,7.159130207061768,, 18500,-0.7029799222946167,7.131732123374939,, 19000,-0.7292678356170654,7.1580196757316585,, 19500,-0.6806507706642151,7.1094029021263125,, 20000,-0.6570433974266052,7.085795381069183,, 20000,,,6.707281188964844,-0.2785292434692383 20500,-0.7204235792160034,7.149175713062286,, 21000,-0.6565122604370117,7.0852641248703,, 21500,-0.6702841520309448,7.099036253452301,, 22000,-0.7068856954574585,7.135637380123138,, 22500,-0.658456027507782,7.087207612514496,, 23000,-0.6618030071258545,7.090554831981659,, 23500,-0.6439463496208191,7.07269818353653,, 24000,-0.6309188604354858,7.059670827865601,, 24500,-0.6609952449798584,7.089747102260589,, 25000,-0.6266164183616638,7.055368631839753,, 25000,,,6.635002207756043,-0.20625026226043702 25500,-0.6183561086654663,7.0471080322265625,, 26000,-0.5877937078475952,7.016545822143555,, 26500,-0.5749752521514893,7.003727053165436,, 27000,-0.6184683442115784,7.0472205834388735,, 27500,-0.5276671051979065,6.956419280052185,, 28000,-0.563706636428833,6.992458676338196,, 28500,-0.534191370010376,6.962943138122559,, 29000,-0.5780285000801086,7.0067806749343875,, 29500,-0.4889846444129944,6.917736486911774,, 30000,-0.5171453952789307,6.945897343635559,, 30000,,,6.570840430259705,-0.14208848476409913 30500,-0.5483458042144775,6.9770976209640505,, 31000,-0.5773682594299316,7.006120066642762,, 31500,-0.5450485348701477,6.973800355434418,, 32000,-0.5045232176780701,6.933275214672088,, 32500,-0.42463943362236023,6.853391424179077,, 33000,-0.4677899181842804,6.896541843891144,, 33500,-0.4655872881412506,6.894339021205902,, 34000,-0.5276547074317932,6.95640665769577,, 34500,-0.5513721108436584,6.9801245727539065,, 35000,-0.5149133205413818,6.943665145397186,, 35000,,,6.562759563922882,-0.1340076184272766 35500,-0.44659581780433655,6.87534773015976,, 36000,-0.44580724835395813,6.874559077739716,, 36500,-0.44718459248542786,6.875936587333679,, 37000,-0.4690369665622711,6.897788933753967,, 37500,-0.3734016716480255,6.802153643131256,, 38000,-0.4559980034828186,6.884749936580658,, 38500,-0.42481374740600586,6.8535656795501705,, 39000,-0.45787784457206726,6.8866300258636475,, 39500,-0.40688517689704895,6.835637136936188,, 40000,-0.4287409484386444,6.857492993354797,, 40000,,,6.492372090816498,-0.06362014532089233 40500,-0.4413072168827057,6.870059115409851,, 41000,-0.47106310725212097,6.899815042495727,, 41500,-0.39017075300216675,6.818922773838043,, 42000,-0.34147122502326965,6.770223379135132,, 42500,-0.3963862359523773,6.825138070106506,, 43000,-0.38573288917541504,6.814484624385834,, 43500,-0.39506101608276367,6.823813135147095,, 44000,-0.4053760766983032,6.834128187179566,, 44500,-0.3949282765388489,6.823680105209351,, 45000,-0.2897488474845886,6.718500811100006,, 45000,,,6.456702638864517,-0.027950693368911744 45500,-0.28094327449798584,6.709695178031922,, 46000,-0.35975590348243713,6.7885076918601985,, 46500,-0.3817383348941803,6.810490349292755,, 47000,-0.39236345887184143,6.821115481853485,, 47500,-0.34790030121803284,6.776652411937714,, 48000,-0.32814332842826843,6.756895285606384,, 48500,-0.30261436104774475,6.73136651468277,, 49000,-0.331712543964386,6.760464302062989,, 49500,-0.29415810108184814,6.722910175323486,, 50000,-0.3133049011230469,6.742057099819183,, 50000,,,6.356075421571732,0.0726765239238739 50500,-0.21287210285663605,6.641624029159546,, 51000,-0.2535097599029541,6.682261671066284,,