step,training/mean_reward,training/mean_global_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward 500,0.07093624025583267,0.07093623805046081,2.1106466896533966,, 1000,0.35044044256210327,0.3504404377937317,1.8311424899101256,, 1500,0.4057343006134033,0.40573426270484925,1.7758486649990082,, 2000,0.40463221073150635,0.40463219714164733,1.77695073056221,, 2500,0.416777104139328,0.41677710676193236,1.764805820941925,, 3000,0.4182462692260742,0.4182462735176086,1.7633366541862487,, 3500,0.457069456577301,0.4570694625377655,1.7245134651660918,, 4000,0.4868566691875458,0.48685666608810424,1.6947262616157532,, 4500,0.4895643889904022,0.4895643720626831,1.6920185556411744,, 5000,0.5153464078903198,0.5153464388847351,1.6662364888191223,, 5000,,,,1.6677577900886535,0.5138251185417175 5500,0.5084236264228821,0.5084236559867858,1.6731592717170716,, 6000,0.5437443852424622,0.5437444455623627,1.6378384821414949,, 6500,0.5628657341003418,0.5628657009601593,1.6187172267436982,, 7000,0.5671544075012207,0.5671544463634491,1.6144284813404084,, 7500,0.5558007955551147,0.5558007400035858,1.6257821877002716,, 8000,0.5599802136421204,0.5599802641868591,1.6216026635169982,, 8500,0.5490528345108032,0.5490528202056885,1.6325301074981688,, 9000,0.5231821537017822,0.5231821308135987,1.6584007968902588,, 9500,0.5143359303474426,0.5143358945846558,1.6672470331192017,, 10000,0.5125994682312012,0.5125994777679443,1.668983449935913,, 10000,,,,1.591383489370346,0.5901994705200195 10500,0.5023519396781921,0.5023520116806031,1.6792309160232544,, 11000,0.45174092054367065,0.45174092435836793,1.7298420033454895,, 11500,0.47742384672164917,0.47742387342453,1.7041590542793275,, 12000,0.44407495856285095,0.44407499289512636,1.737507934808731,, 12500,0.44063135981559753,0.44063133430480955,1.7409515933990478,, 13000,0.42060035467147827,0.4206003739833832,1.7609825537204742,, 13500,0.48042017221450806,0.4804201757907867,1.7011627519130708,, 14000,0.4640040099620819,0.4640039782524109,1.7175789494514466,, 14500,0.4569120705127716,0.4569120831489563,1.724670844554901,, 15000,0.4771478772163391,0.47714788818359377,1.7044350395202637,, 15000,,,,1.5979940903186798,0.5835888385772705 15500,0.49387720227241516,0.49387721490859987,1.6877057127952575,, 16000,0.4772421717643738,0.4772421736717224,1.704340754032135,, 16500,0.4969182014465332,0.49691821789741514,1.6846647098064422,, 17000,0.522396981716156,0.5223969957828521,1.6591859319210052,, 17500,0.5762758255004883,0.5762759037017823,1.6053070240020753,, 18000,0.5090916156768799,0.5090916159152985,1.672491311788559,, 18500,0.5028951168060303,0.5028951501846314,1.6786877775192262,, 19000,0.41750773787498474,0.41750779151916506,1.7640751361846925,, 19500,0.5379828214645386,0.5379828279018402,1.6436000998020173,, 20000,0.5571663975715637,0.5571663298606873,1.6244165978431702,, 20000,,,,1.608021138906479,0.5735617876052856 20500,0.5661811232566833,0.566181179523468,1.6154017481803895,, 21000,0.5516728758811951,0.5516728448867798,1.6299100828170776,, 21500,0.543187141418457,0.5431871364116668,1.6383957912921905,, 22000,0.5424355864524841,0.5424355940818787,1.6391473336219788,, 22500,0.46391692757606506,0.46391697430610657,1.7176659533977507,, 23000,0.5669492483139038,0.5669491815567017,1.6146337461471558,, 23500,0.5498377680778503,0.5498377583026886,1.6317451694011689,, 24000,0.5231595635414124,0.523159553527832,1.6584233741760255,, 24500,0.5734352469444275,0.5734352788925171,1.6081476488113404,, 25000,0.5841834545135498,0.5841834576129913,1.597399470090866,, 25000,,,,1.6018342000246049,0.5797487497329712 25500,0.5548990368843079,0.5548990595340729,1.6266838681697846,, 26000,0.5489537715911865,0.548953780412674,1.6326291472911836,, 26500,0.523786723613739,0.5237867088317871,1.6577962188720703,, 27000,0.5326566696166992,0.532656691789627,1.6489262359142303,, 27500,0.4980747103691101,0.49807472157478333,1.683508206129074,, 28000,0.5279725790023804,0.5279725823402405,1.6536103453636168,, 28500,0.5231752991676331,0.5231753733158112,1.6584075543880463,, 29000,0.5257567167282104,0.525756727218628,1.6558262004852295,, 29500,0.5360366106033325,0.5360366177558898,1.6455463099479675,, 30000,0.5296390056610107,0.5296390047073364,1.651943922996521,, 30000,,,,1.648978328704834,0.5326045751571655 30500,0.5064873695373535,0.5064873526096344,1.6750955750942231,, 31000,0.5016857385635376,0.5016857168674469,1.6798972108364105,, 31500,0.4948207437992096,0.4948207240104675,1.6867622036933898,, 32000,0.47074687480926514,0.47074691534042357,1.7108360123634339,, 32500,0.48794129490852356,0.48794123363494873,1.6936416940689087,, 33000,0.47818341851234436,0.4781834349632263,1.703399492740631,, 33500,0.44767534732818604,0.44767537927627565,1.7339075484275819,, 34000,0.47615739703178406,0.4761574161052704,1.705425511598587,, 34500,0.4326949417591095,0.4326949303150177,1.7488879973888398,, 35000,0.4924500584602356,0.492450110912323,1.6891328167915345,, 35000,,,,1.8465376287698745,0.33504530787467957 35500,0.49262481927871704,0.49262481451034545,1.6889581131935119,, 36000,0.5065568685531616,0.5065568814277649,1.6750260462760926,, 36500,0.5447832345962524,0.5447833125591278,1.6367996151447297,, 37000,0.5058397650718689,0.5058397567272186,1.6757431709766388,, 37500,0.4945389926433563,0.4945389769077301,1.6870439507961272,, 38000,0.4948802888393402,0.4948802709579468,1.6867026567459107,, 38500,0.4787149131298065,0.47871492576599123,1.7028680019378661,, 39000,0.5089614391326904,0.5089615104198456,1.672621417284012,, 39500,0.4510083496570587,0.4510083889961243,1.7305745387077331,, 40000,0.456036776304245,0.45603679895401,1.7255461287498475,, 40000,,,,1.8901805287599565,0.2914023995399475 40500,0.4575580954551697,0.45755811762809756,1.7240248100757598,, 41000,0.4873286187648773,0.487328556060791,1.6942543716430665,, 41500,0.43459874391555786,0.4345987572669983,1.7469841704368592,, 42000,0.42329326272010803,0.42329330134391785,1.7582896263599397,, 42500,0.4241865575313568,0.42418656539916993,1.7573963623046875,, 43000,0.42715826630592346,0.42715827822685243,1.754424649477005,, 43500,0.4470759630203247,0.4470759456157684,1.734506982088089,, 44000,0.3330603539943695,0.33306037640571595,1.8485225512981416,, 44500,0.3125154376029968,0.31251542043685915,1.8690675072669982,, 45000,0.4729625880718231,0.4729626190662384,1.708620308637619,, 45000,,,,1.7649959480762483,0.4165869355201721 45500,0.5250033736228943,0.5250033700466156,1.6565795576572417,, 46000,0.5290964245796204,0.5290964612960816,1.6524864664077759,, 46500,0.5228501558303833,0.5228501555919647,1.6587327721118927,, 47000,0.5069420337677002,0.5069420521259308,1.6746408755779267,, 47500,0.4779704511165619,0.4779704854488373,1.70361244225502,, 48000,0.481550395488739,0.4815504078865051,1.7000325198173523,, 48500,0.43010956048965454,0.43010956192016603,1.7514733657836914,, 49000,0.47280097007751465,0.47280096244812014,1.7087819652557372,, 49500,0.5190454125404358,0.5190454034805297,1.6625375242233276,, 50000,0.5024909973144531,0.5024910089969635,1.679091918706894,, 50000,,,,1.6288189888000488,0.5527639389038086