step,training/mean_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward 500,-0.05090157687664032,4.946821364402771,, 1000,-0.04170242324471474,4.937622226715088,, 1500,-0.05500293895602226,4.950922730445861,, 2000,-0.018688300624489784,4.9146081104278565,, 2500,-0.05426694452762604,4.950186742782593,, 3000,-0.025031087920069695,4.920950884819031,, 3500,-0.008072452619671822,4.9039922542572025,, 4000,-0.004932711832225323,4.900852511405945,, 4500,0.00432644272223115,4.891593357086181,, 5000,0.025606250390410423,4.870313549995422,, 5000,,,4.748536834716797,0.14738296508789062 5500,0.014778410084545612,4.8811413898468015,, 6000,0.03728498890995979,4.858634803771973,, 6500,0.045450400561094284,4.850469432830811,, 7000,0.09925542026758194,4.79666444015503,, 7500,0.06711018085479736,4.82880956363678,, 8000,0.12257778644561768,4.773342052459717,, 8500,0.15071412920951843,4.745205780982971,, 9000,0.16793929040431976,4.727980485916138,, 9500,0.1717674732208252,4.724152348518372,, 10000,0.2648695111274719,4.631050242900848,, 10000,,,4.464053330421447,0.43186646938323975 10500,0.29978781938552856,4.5961320705413815,, 11000,0.3991960883140564,4.496723872184753,, 11500,0.44489067792892456,4.451028926849365,, 12000,0.48265042901039124,4.41326952791214,, 12500,0.3544653058052063,4.541454402923584,, 13000,0.4819711446762085,4.413948875904083,, 13500,0.5346062183380127,4.3613138384819035,, 14000,0.5325151085853577,4.363404850006104,, 14500,0.5105998516082764,4.385319903850555,, 15000,0.5004657506942749,4.395453908443451,, 15000,,,4.357265269756317,0.5386545300483704 15500,0.5016806125640869,4.394239304542541,, 16000,0.5715159773826599,4.324403958797455,, 16500,0.5203468203544617,4.375572797298432,, 17000,0.5837644338607788,4.312155207633972,, 17500,0.5970160365104675,4.298903336524964,, 18000,0.5681489109992981,4.327770755290985,, 18500,0.5582693815231323,4.337650377750396,, 19000,0.5308208465576172,4.365098962306976,, 19500,0.5906524658203125,4.3052672653198245,, 20000,0.5454909205436707,4.35042905330658,, 20000,,,4.1880436098575595,0.7078761899471283 20500,0.6124237775802612,4.283496038913727,, 21000,0.6063739061355591,4.289545930862427,, 21500,0.718097448348999,4.177822423934937,, 22000,0.6606463193893433,4.2352732815742495,, 22500,0.63279128074646,4.26312879228592,, 23000,0.6569719314575195,4.238947916507721,, 23500,0.6903178691864014,4.205601337909698,, 24000,0.6854216456413269,4.210498442173004,, 24500,0.4987829625606537,4.397136566638946,, 25000,0.5834265947341919,4.312493271350861,, 25000,,,4.265715123414993,0.6302046763896942 25500,0.6333773136138916,4.262542848110199,, 26000,0.6650903224945068,4.230829482555389,, 26500,0.7007908821105957,4.1951290159225465,, 27000,0.7745119333267212,4.121407799243927,, 27500,0.5535902380943298,4.342329843044281,, 28000,0.727649450302124,4.168270427227021,, 28500,0.7028014659881592,4.193118199825287,, 29000,0.7065593600273132,4.189360683441162,, 29500,0.6917510628700256,4.204168540000915,, 30000,0.6952394247055054,4.200680503845215,, 30000,,,4.141589639186859,0.7543301606178283 30500,0.7955432534217834,4.100376103401184,, 31000,0.7612375020980835,4.134682499408722,, 31500,0.7284286618232727,4.167491149425507,, 32000,0.7315862774848938,4.164333153247833,, 32500,0.7347390055656433,4.1611808395385745,, 33000,0.7418614625930786,4.15405862569809,, 33500,0.7890051007270813,4.1069148797988895,, 34000,0.6841253638267517,4.21179453086853,, 34500,0.7905815839767456,4.1053377966880795,, 35000,0.7712089419364929,4.124711304187775,, 35000,,,4.142136974334717,0.7537828254699707 35500,0.6822840571403503,4.213635506629944,, 36000,0.8439620733261108,4.051957638740539,, 36500,0.7523859739303589,4.143533845901489,, 37000,0.7203350067138672,4.175584668636322,, 37500,0.6816504001617432,4.214270025253296,, 38000,0.7546802759170532,4.141239542484284,, 38500,0.7598051428794861,4.136114589691162,, 39000,0.5846160650253296,4.311303897857666,, 39500,0.7186543941497803,4.1772658305168155,, 40000,0.7202681303024292,4.175651653289795,, 40000,,,4.119672214984893,0.7762475848197937 40500,0.7293861508369446,4.166533496379852,, 41000,0.7097687721252441,4.186150917053222,, 41500,0.7109078764915466,4.18501173210144,, 42000,0.7033184170722961,4.192601573944092,, 42500,0.7506208419799805,4.145299172878265,, 43000,0.5899915099143982,4.305928323745728,, 43500,0.5647913813591003,4.33112840461731,, 44000,0.7687448263168335,4.127174705982208,, 44500,0.6942294239997864,4.201690705299377,, 45000,0.7825618982315063,4.113358335018158,, 45000,,,4.108089048862457,0.7878307509422302 45500,0.7802777290344238,4.115642543315888,, 46000,0.7647122144699097,4.131207253932953,, 46500,0.7805477976799011,4.115372149944306,, 47000,0.8415427803993225,4.0543761372566225,, 47500,0.820213794708252,4.075706208705902,, 48000,0.7652164101600647,4.130703283786774,, 48500,0.7186154723167419,4.177304429531097,, 49000,0.7521359324455261,4.143783277988434,, 49500,0.7244331240653992,4.171486785411835,, 50000,0.7121034860610962,4.1838162541389465,, 50000,,,4.130136134624482,0.7657836651802064