| step,training/mean_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward | |
| 500,-0.096152164041996,4.99207195186615,, | |
| 1000,-0.06512361019849777,4.96104340839386,, | |
| 1500,-0.08414873480796814,4.980068560600281,, | |
| 2000,-0.09948242455720901,4.995402176856994,, | |
| 2500,-0.043631017208099365,4.939550826072693,, | |
| 3000,-0.03869183734059334,4.934611623764038,, | |
| 3500,-0.06258752942085266,4.958507365226746,, | |
| 4000,-0.07527678459882736,4.971196619987488,, | |
| 4500,-0.015339150093495846,4.911258949279786,, | |
| 5000,-0.0179694015532732,4.913889200210571,, | |
| 5000,,,4.800247411727906,0.09567238807678223 | |
| 5500,-0.0029463176615536213,4.898866117477417,, | |
| 6000,0.0015369720058515668,4.894382827758789,, | |
| 6500,0.017811225727200508,4.878108571052551,, | |
| 7000,0.028551345691084862,4.867368447303772,, | |
| 7500,0.033395349979400635,4.862524446487427,, | |
| 8000,0.049447450786828995,4.846472362041474,, | |
| 8500,0.07716485857963562,4.8187549114227295,, | |
| 9000,0.07459525018930435,4.821324524879455,, | |
| 9500,0.04871981218457222,4.847200005054474,, | |
| 10000,0.060915492475032806,4.835004302978516,, | |
| 10000,,,4.66095477104187,0.23496502876281739 | |
| 10500,0.10497047007083893,4.790949280738831,, | |
| 11000,0.13691678643226624,4.759002935409546,, | |
| 11500,0.09497728943824768,4.800942517280578,, | |
| 12000,0.0881446972489357,4.807775067329406,, | |
| 12500,0.14356255531311035,4.752357314586639,, | |
| 13000,0.13371999561786652,4.762199838638305,, | |
| 13500,0.17861317098140717,4.71730668592453,, | |
| 14000,0.17360711097717285,4.722312721252441,, | |
| 14500,0.14575694501399994,4.7501628789901735,, | |
| 15000,0.1765642911195755,4.719355390071869,, | |
| 15000,,,4.494689228534699,0.401230571269989 | |
| 15500,0.1841064691543579,4.711813358306885,, | |
| 16000,0.20472972095012665,4.691190200805664,, | |
| 16500,0.21519644558429718,4.680723492145538,, | |
| 17000,0.22622603178024292,4.669693725585938,, | |
| 17500,0.23271916806697845,4.663200649738312,, | |
| 18000,0.20825894176959991,4.687660883426666,, | |
| 18500,0.20655514299869537,4.689364548683167,, | |
| 19000,0.23550231754779816,4.660417581558227,, | |
| 19500,0.24044354259967804,4.655476234912872,, | |
| 20000,0.264285683631897,4.631634031772614,, | |
| 20000,,,4.378414504528045,0.5175052952766418 | |
| 20500,0.24257871508598328,4.653341067790985,, | |
| 21000,0.2734198570251465,4.6224999294281,, | |
| 21500,0.2993412911891937,4.596578509807586,, | |
| 22000,0.2575041651725769,4.638415655136108,, | |
| 22500,0.2889156639575958,4.607004048824311,, | |
| 23000,0.2913220524787903,4.6045977711677555,, | |
| 23500,0.2931461036205292,4.602773674488068,, | |
| 24000,0.3140698969364166,4.58184977722168,, | |
| 24500,0.2815248966217041,4.614394765377044,, | |
| 25000,0.34275874495506287,4.553161077022552,, | |
| 25000,,,4.3280693113803865,0.5678504884243012 | |
| 25500,0.33959951996803284,4.556320146560669,, | |
| 26000,0.2958771288394928,4.600042628288269,, | |
| 26500,0.3365664482116699,4.559353630065918,, | |
| 27000,0.39216136932373047,4.503758285522461,, | |
| 27500,0.3526252508163452,4.543294489860535,, | |
| 28000,0.32642266154289246,4.5694971489906315,, | |
| 28500,0.3240317702293396,4.571888098239898,, | |
| 29000,0.3990623354911804,4.496857488155365,, | |
| 29500,0.38512489199638367,4.510795005321503,, | |
| 30000,0.4018428325653076,4.49407683801651,, | |
| 30000,,,4.15780279636383,0.738117003440857 | |
| 30500,0.4216274619102478,4.474292592048645,, | |
| 31000,0.4425486624240875,4.4533711500167845,, | |
| 31500,0.4334653913974762,4.4624542346000675,, | |
| 32000,0.40989288687705994,4.486026713848114,, | |
| 32500,0.4478788673877716,4.448040902137756,, | |
| 33000,0.38284221291542053,4.513077600002289,, | |
| 33500,0.4320956766605377,4.4638239521980285,, | |
| 34000,0.4388431906700134,4.457076811313629,, | |
| 34500,0.4430956244468689,4.452824223995209,, | |
| 35000,0.42910146713256836,4.46681832742691,, | |
| 35000,,,4.068916796445847,0.8270030033588409 | |
| 35500,0.4874376654624939,4.408482096195221,, | |
| 36000,0.4443487823009491,4.4515708994865415,, | |
| 36500,0.5012847185134888,4.394635180950165,, | |
| 37000,0.4638333022594452,4.4320868330001835,, | |
| 37500,0.4079974591732025,4.487922326564789,, | |
| 38000,0.48431918025016785,4.41160058259964,, | |
| 38500,0.5015220642089844,4.394397593975067,, | |
| 39000,0.4871424734592438,4.408777257442474,, | |
| 39500,0.5387521982192993,4.357167680740356,, | |
| 40000,0.521673321723938,4.374246698379516,, | |
| 40000,,,4.046344268321991,0.8495755314826965 | |
| 40500,0.4830525815486908,4.412867218971252,, | |
| 41000,0.5307802557945251,4.365139339447022,, | |
| 41500,0.4910406768321991,4.404878987312317,, | |
| 42000,0.5532412528991699,4.3426783723831175,, | |
| 42500,0.4816476106643677,4.414272374629975,, | |
| 43000,0.6063985228538513,4.289521210193634,, | |
| 43500,0.5064314007759094,4.389488296508789,, | |
| 44000,0.5625852942466736,4.333334600925445,, | |
| 44500,0.4958391487598419,4.400080798625946,, | |
| 45000,0.5854656100273132,4.3104542813301086,, | |
| 45000,,,4.055965973138809,0.8399538266658783 | |
| 45500,0.6361018419265747,4.259818017482758,, | |
| 46000,0.5547290444374084,4.341190773963929,, | |
| 46500,0.5512343645095825,4.344685324192048,, | |
| 47000,0.5476009249687195,4.3483191895484925,, | |
| 47500,0.6217708587646484,4.274149246215821,, | |
| 48000,0.5564359426498413,4.339484111309051,, | |
| 48500,0.560309648513794,4.335610082626343,, | |
| 49000,0.6254128217697144,4.270506847381592,, | |
| 49500,0.6034451723098755,4.2924743361473086,, | |
| 50000,0.6424245238304138,4.253495495796203,, | |
| 50000,,,4.036076542139053,0.8598432576656342 | |
| 50500,0.5849865078926086,4.310933550834656,, | |
| 51000,0.6628747582435608,4.233045032024384,, | |