step,training/mean_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward 500,-0.8617738485336304,7.290525542259216,, 1000,-0.8452112078666687,7.273963315010071,, 1500,-0.8646326065063477,7.293385138511658,, 2000,-0.899966299533844,7.328718534946441,, 2500,-0.8617415428161621,7.290493832588195,, 3000,-0.8524464964866638,7.281198422908783,, 3500,-0.8608368635177612,7.289588628292083,, 4000,-0.9257076382637024,7.354459602355957,, 4500,-0.8679414391517639,7.296693793296814,, 5000,-0.857245683670044,7.285997250080109,, 5000,,,6.976683931350708,-0.5479319858551025 5500,-0.8875183463096619,7.316270917892456,, 6000,-0.8504537343978882,7.279205327510834,, 6500,-0.826412558555603,7.2551643452644345,, 7000,-0.8518283367156982,7.280580249786377,, 7500,-0.8202617168426514,7.249013989448548,, 8000,-0.8396432399749756,7.268395166397095,, 8500,-0.7691933512687683,7.197945049285889,, 9000,-0.8671407699584961,7.295892025947571,, 9500,-0.8188203573226929,7.247572443008423,, 10000,-0.8152974843978882,7.244049181461334,, 10000,,,6.935034551620483,-0.506282606124878 10500,-0.7675607800483704,7.196313279151917,, 11000,-0.7082782983779907,7.137030204772949,, 11500,-0.7528547048568726,7.181606856822968,, 12000,-0.8023167848587036,7.231068401813507,, 12500,-0.7357965111732483,7.164548551559448,, 13000,-0.7120620012283325,7.1408142848014835,, 13500,-0.7472229599952698,7.175975122451782,, 14000,-0.7448320984840393,7.173584147453308,, 14500,-0.7235937118530273,7.152346004962921,, 15000,-0.6996985077857971,7.128450479030609,, 15000,,,6.869992580413818,-0.4412406349182129 15500,-0.7101902961730957,7.138942234039306,, 16000,-0.7614399194717407,7.190192145347595,, 16500,-0.7656301856040955,7.194381726264954,, 17000,-0.6625266671180725,7.091278978347779,, 17500,-0.7567625641822815,7.185514679431916,, 18000,-0.740471363067627,7.169223729133606,, 18500,-0.6846411824226379,7.1133931999206546,, 19000,-0.6844273805618286,7.113179267883301,, 19500,-0.6730723977088928,7.101824669361115,, 20000,-0.5798686742782593,7.008620673656464,, 20000,,,6.813299129009247,-0.38454718351364137 20500,-0.7014344334602356,7.130186430931091,, 21000,-0.7141661047935486,7.142917767047882,, 21500,-0.7107889652252197,7.139540870189666,, 22000,-0.6676903367042542,7.096442198276519,, 22500,-0.6966897249221802,7.1254414319992065,, 23000,-0.5901539921760559,7.018905898094177,, 23500,-0.6942910552024841,7.123043063163757,, 24000,-0.674022376537323,7.102774487495422,, 24500,-0.5780402421951294,7.006792423725128,, 25000,-0.5507301092147827,6.979482293128967,, 25000,,,6.814141434431076,-0.3853894889354706 25500,-0.5942418575286865,7.022993886470795,, 26000,-0.629651665687561,7.058403550624847,, 26500,-0.6375637650489807,7.066316032409668,, 27000,-0.5717037320137024,7.000455228328705,, 27500,-0.7358771562576294,7.164629065513611,, 28000,-0.6557050943374634,7.08445668554306,, 28500,-0.5623023509979248,6.991054008007049,, 29000,-0.6083151698112488,7.037066901683807,, 29500,-0.5630723237991333,6.99182436132431,, 30000,-0.5851019024848938,7.013853661060333,, 30000,,,6.77483168721199,-0.3460797417163849 30500,-0.5622897744178772,6.991041760921478,, 31000,-0.552385687828064,6.981137783527374,, 31500,-0.5442359447479248,6.972987968921661,, 32000,-0.5469315648078918,6.975683079719543,, 32500,-0.6113210320472717,7.040073129653931,, 33000,-0.49891865253448486,6.927670560359955,, 33500,-0.5630372166633606,6.99178911113739,, 34000,-0.549182653427124,6.977934645175933,, 34500,-0.5194879174232483,6.948240106105804,, 35000,-0.5178032517433167,6.946554842948913,, 35000,,,6.547697970867157,-0.11894602537155151 35500,-0.5397603511810303,6.9685123620033265,, 36000,-0.4920336604118347,6.920785859107971,, 36500,-0.5223620533943176,6.951114001750946,, 37000,-0.5050075650215149,6.933759840965271,, 37500,-0.4617321491241455,6.890483835220337,, 38000,-0.5022106170654297,6.930962489128113,, 38500,-0.5244693160057068,6.953221343517304,, 39000,-0.4975418448448181,6.926293531894684,, 39500,-0.45425209403038025,6.883004150867462,, 40000,-0.5278385877609253,6.956590285301209,, 40000,,,6.528427226543426,-0.09967528104782104 40500,-0.5257444381713867,6.954496334075928,, 41000,-0.38926562666893005,6.8180176863670345,, 41500,-0.43045225739479065,6.859204209804535,, 42000,-0.4999323785305023,6.928684387683869,, 42500,-0.4386138617992401,6.867365935325623,, 43000,-0.47823774814605713,6.906989810943603,, 43500,-0.4113224446773529,6.840074440002441,, 44000,-0.3545737564563751,6.783325706958771,, 44500,-0.2791075110435486,6.707859438896179,, 45000,-0.39966776967048645,6.828419557094574,, 45000,,,6.501550400257111,-0.07279845476150512 45500,-0.33836689591407776,6.767118937492371,, 46000,-0.40727633237838745,6.836028409957886,, 46500,-0.33732089400291443,6.766072798252106,, 47000,-0.4030410945415497,6.831793323993683,, 47500,-0.32430291175842285,6.753054868221283,, 48000,-0.45153647661209106,6.880288582324981,, 48500,-0.29386699199676514,6.722618891716003,, 49000,-0.4064384996891022,6.83519031047821,, 49500,-0.3218232989311218,6.750575186252594,, 50000,-0.356376051902771,6.785128007888794,, 50000,,,6.403433907032013,0.02531803846359253 50500,-0.34362977743148804,6.772381739139557,, 51000,-0.3821800947189331,6.810932026863098,,