step,training/mean_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward 500,-0.8263617157936096,7.255113495826722,, 1000,-0.9067127108573914,7.335464511871338,, 1500,-0.8828868865966797,7.311639536380768,, 2000,-0.889229953289032,7.317981565952301,, 2500,-0.8690732717514038,7.297824895381927,, 3000,-0.8268213272094727,7.255573151111602,, 3500,-0.8827632665634155,7.311515277385712,, 4000,-0.9065147042274475,7.335266833305359,, 4500,-0.8194532990455627,7.2482057390213015,, 5000,-0.8882007598876953,7.316952527999878,, 5000,,,6.869273407459259,-0.44052146196365355 5500,-0.8687885403633118,7.297540441036224,, 6000,-0.8623587489128113,7.291110960483551,, 6500,-0.8633607625961304,7.292112612247467,, 7000,-0.8410907983779907,7.26984258890152,, 7500,-0.8229678273200989,7.251719489097595,, 8000,-0.7651295065879822,7.193881477832794,, 8500,-0.8509804606437683,7.279732403278351,, 9000,-0.8001350164413452,7.228886924266815,, 9500,-0.7962088584899902,7.224960691928864,, 10000,-0.7528386116027832,7.181590190410614,, 10000,,,6.79160849571228,-0.3628565502166748 10500,-0.7547966837882996,7.183548920154571,, 11000,-0.7543827295303345,7.183135050296784,, 11500,-0.7926624417304993,7.221414047241211,, 12000,-0.7878916263580322,7.21664364862442,, 12500,-0.8054863214492798,7.234238289356232,, 13000,-0.7041719555854797,7.132923555374146,, 13500,-0.7880141139030457,7.216765927791595,, 14000,-0.7437142133712769,7.172466307163239,, 14500,-0.7415310740470886,7.170283306598663,, 15000,-0.7167900800704956,7.145541779518127,, 15000,,,6.710041258335114,-0.28128931283950803 15500,-0.7100265026092529,7.138778553962707,, 16000,-0.6699981093406677,7.098750121116638,, 16500,-0.6853976845741272,7.114149363517761,, 17000,-0.6669694781303406,7.095721548080444,, 17500,-0.7278253436088562,7.156577161312104,, 18000,-0.7458333373069763,7.174585083007813,, 18500,-0.639943540096283,7.068695529937744,, 19000,-0.6681294441223145,7.09688152551651,, 19500,-0.6554566025733948,7.084208698272705,, 20000,-0.6474620699882507,7.076213788032532,, 20000,,,6.724071929454803,-0.295319983959198 20500,-0.5796695351600647,7.008421193122864,, 21000,-0.6132455468177795,7.0419976906776425,, 21500,-0.641316294670105,7.070068125247955,, 22000,-0.6070537567138672,7.035805828094483,, 22500,-0.6213082671165466,7.050060187339783,, 23000,-0.5987069606781006,7.027459043502808,, 23500,-0.5634963512420654,6.992248404026031,, 24000,-0.656582772731781,7.085334436416626,, 24500,-0.6128666400909424,7.041618705749512,, 25000,-0.602614164352417,7.031366103649139,, 25000,,,6.522448718547821,-0.09369677305221558 25500,-0.6478380560874939,7.076589860916138,, 26000,-0.5294618606567383,6.958213946342468,, 26500,-0.5772883296012878,7.006040181159973,, 27000,-0.5802437663078308,7.008995519161225,, 27500,-0.5587286949157715,6.987480537891388,, 28000,-0.5751935839653015,7.0039453482627865,, 28500,-0.5746445059776306,7.003396744251251,, 29000,-0.5232771039009094,6.952028768539429,, 29500,-0.5493292212486267,6.978081292152405,, 30000,-0.503221869468689,6.931973974704743,, 30000,,,6.429423696994782,-0.0006717514991760254 30500,-0.5051377415657043,6.9338896379470825,, 31000,-0.4982759952545166,6.927027789115906,, 31500,-0.4646431803703308,6.89339541387558,, 32000,-0.5504353046417236,6.979187340736389,, 32500,-0.5156800150871277,6.944431600093842,, 33000,-0.56882244348526,6.997574350833893,, 33500,-0.4425891637802124,6.871341067790985,, 34000,-0.47219014167785645,6.900942064285278,, 34500,-0.5019736289978027,6.93072540473938,, 35000,-0.5141976475715637,6.942949749946594,, 35000,,,6.395660092830658,0.03309185266494751 35500,-0.48715510964393616,6.915907111167908,, 36000,-0.4913508892059326,6.920102861404419,, 36500,-0.501092255115509,6.92984422492981,, 37000,-0.4121609926223755,6.840912886619568,, 37500,-0.4394935667514801,6.8682457504272465,, 38000,-0.4851919114589691,6.913944004535675,, 38500,-0.37667229771614075,6.805424425601959,, 39000,-0.42553624510765076,6.85428814792633,, 39500,-0.40949469804763794,6.838246612071991,, 40000,-0.37139028310775757,6.800142294406891,, 40000,,,6.353951736688614,0.07480020880699158 40500,-0.40079405903816223,6.82954583120346,, 41000,-0.5057007670402527,6.934452698707581,, 41500,-0.40369710326194763,6.832449185848236,, 42000,-0.39793574810028076,6.826687603473664,, 42500,-0.34493279457092285,6.7736849493980404,, 43000,-0.37739047408103943,6.8061424264907835,, 43500,-0.3802774250507355,6.809029284000396,, 44000,-0.3029611110687256,6.731713123798371,, 44500,-0.2817641496658325,6.710516110420227,, 45000,-0.36605900526046753,6.794810812950134,, 45000,,,6.4578825998306275,-0.029130654335021974 45500,-0.33587846159935,6.7646303915977475,, 46000,-0.2551456689834595,6.683897601127624,, 46500,-0.2449646294116974,6.673716594219208,, 47000,-0.31473472714424133,6.743486792564392,, 47500,-0.3752383887767792,6.80399045753479,, 48000,-0.21358035504817963,6.642332258224488,, 48500,-0.32369568943977356,6.752447659492493,, 49000,-0.3818131983280182,6.81056510066986,, 49500,-0.25846466422080994,6.6872166080474855,, 50000,-0.32450661063194275,6.75325867652893,, 50000,,,6.366485278606415,0.06226666688919067 50500,-0.3382641077041626,6.767015898227692,, 51000,-0.25530362129211426,6.68405544424057,,