step,training/mean_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward 500,-0.10296709835529327,4.998886919021606,, 1000,-0.06666817516088486,4.96258797454834,, 1500,-0.10364072024822235,4.999560488700867,, 2000,-0.052242711186409,4.948162551879883,, 2500,-0.06379162520170212,4.959711435317993,, 3000,-0.03978344798088074,4.93570327091217,, 3500,-0.03653227165341377,4.932452056884766,, 4000,-0.06587694585323334,4.961796805381775,, 4500,-0.022480586543679237,4.9184003896713255,, 5000,-0.009504017420113087,4.9054238204956055,, 5000,,,4.792796535491943,0.10312326431274414 5500,-0.0066718971356749535,4.902591695785523,, 6000,-0.03311249613761902,4.929032302856445,, 6500,0.03438558056950569,4.8615342016220096,, 7000,0.0339495912194252,4.861970207691193,, 7500,0.03034530207514763,4.865574484825134,, 8000,0.02195901796221733,4.873960786819458,, 8500,0.060357946902513504,4.835561883926392,, 9000,0.07625476270914078,4.819665023326873,, 9500,0.06478898972272873,4.831130790233612,, 10000,0.06489921361207962,4.831020574569703,, 10000,,,4.666431403160095,0.22948839664459228 10500,0.10255999118089676,4.793359787464142,, 11000,0.06854269653558731,4.827377107143402,, 11500,0.06884796172380447,4.82707186126709,, 12000,0.1288679540157318,4.767051860809326,, 12500,0.06688282638788223,4.829036946296692,, 13000,0.11734893918037415,4.778570848941803,, 13500,0.11552879959344864,4.780390933036804,, 14000,0.1304216831922531,4.765498089790344,, 14500,0.13354440033435822,4.762375334262848,, 15000,0.1489202231168747,4.7469996099472045,, 15000,,,4.5521431827545165,0.3437766170501709 15500,0.1578059196472168,4.7381138467788695,, 16000,0.17461705207824707,4.72130270242691,, 16500,0.17276881635189056,4.723150907039642,, 17000,0.21657778322696686,4.679341924667359,, 17500,0.17617830634117126,4.719741429805755,, 18000,0.17349135875701904,4.722428479194641,, 18500,0.19552209973335266,4.7003977227211,, 19000,0.20191137492656708,4.694008372783661,, 19500,0.23065224289894104,4.665267523288727,, 20000,0.21148616075515747,4.684433532714844,, 20000,,,4.521033565998078,0.3748862338066101 20500,0.2121000587940216,4.683819647789002,, 21000,0.2417314350605011,4.654188365459442,, 21500,0.214140847325325,4.681778971672058,, 22000,0.24620017409324646,4.649719645500183,, 22500,0.252514123916626,4.6434057970047,, 23000,0.25154685974121094,4.644372911453247,, 23500,0.32467982172966003,4.571240062236786,, 24000,0.2569233477115631,4.6389964504241945,, 24500,0.2598339915275574,4.636085933208466,, 25000,0.32823413610458374,4.567685722827911,, 25000,,,4.296476117372513,0.5994436824321747 25500,0.2690514624118805,4.626868526458741,, 26000,0.3998478651046753,4.496072246074677,, 26500,0.319585382938385,4.576334467887879,, 27000,0.3193495571613312,4.576570370197296,, 27500,0.3812367022037506,4.514683204174042,, 28000,0.32334744930267334,4.57257230091095,, 28500,0.3267737030982971,4.569146003246307,, 29000,0.44070178270339966,4.455217948913575,, 29500,0.4353683590888977,4.460551528453827,, 30000,0.4437393546104431,4.45218066072464,, 30000,,,4.236682058572769,0.6592377412319184 30500,0.33050891757011414,4.565410851955414,, 31000,0.37575894594192505,4.520160816192627,, 31500,0.37192198634147644,4.523998051166535,, 32000,0.3543042242527008,4.541615476608277,, 32500,0.35987070202827454,4.536049204349518,, 33000,0.4516426622867584,4.444277173995972,, 33500,0.38735029101371765,4.508569660186768,, 34000,0.4188733994960785,4.477046539783478,, 34500,0.4230087995529175,4.472911113262176,, 35000,0.5553001761436462,4.3406193008422855,, 35000,,,4.118920311927796,0.7769994878768921 35500,0.43865877389907837,4.457260857105255,, 36000,0.4685744643211365,4.427345354080201,, 36500,0.44665393233299255,4.449265954494476,, 37000,0.47251421213150024,4.4234056115150455,, 37500,0.45665276050567627,4.439267342567444,, 38000,0.5514242053031921,4.344495559692382,, 38500,0.45464465022087097,4.4412752618789675,, 39000,0.500196635723114,4.395723334312439,, 39500,0.45103955268859863,4.444880160331726,, 40000,0.5860480666160583,4.309871883392334,, 40000,,,4.12712788939476,0.7687919104099273 40500,0.5355574488639832,4.360362471580506,, 41000,0.5203912258148193,4.3755286521911625,, 41500,0.45988547801971436,4.4360346012115475,, 42000,0.5189467072486877,4.376973116397858,, 42500,0.4407755434513092,4.45514430475235,, 43000,0.5440132021903992,4.35190699005127,, 43500,0.5349785089492798,4.360941344261169,, 44000,0.5691167712211609,4.32680325126648,, 44500,0.5934106707572937,4.30250892496109,, 45000,0.5653696656227112,4.330550084590912,, 45000,,,4.110186086893082,0.7857337129116059 45500,0.5900925397872925,4.30582715177536,, 46000,0.6625041961669922,4.233415371417999,, 46500,0.5841211080551147,4.311798721313477,, 47000,0.5963178873062134,4.299601813316345,, 47500,0.653396725654602,4.242522513389587,, 48000,0.5921937823295593,4.303725955486297,, 48500,0.5917907953262329,4.304129277706147,, 49000,0.6084296703338623,4.28749037694931,, 49500,0.6373558640480042,4.258563662528991,, 50000,0.641218364238739,4.2547016582489015,, 50000,,,4.059773937463761,0.8361458623409271 50500,0.6017117500305176,4.294208214759827,, 51000,0.6168948411941528,4.279025114059448,,