step,training/mean_reward,training/mean_global_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward 500,-0.03450341895222664,-0.034503421783447265,2.21608633852005,, 1000,-0.04744487628340721,-0.04744487380981445,2.2290278015136717,, 1500,-0.07780329138040543,-0.07780329942703247,2.259386221885681,, 2000,-0.06185987964272499,-0.06185988235473633,2.2434428148269654,, 2500,-0.014688276685774326,-0.014688277721405029,2.1962711925506593,, 3000,-0.0866512879729271,-0.08665128946304321,2.268234219074249,, 3500,-0.045226745307445526,-0.045226747989654544,2.2268096861839295,, 4000,-0.05605094134807587,-0.05605093860626221,2.2376338682174683,, 4500,-0.01419476605951786,-0.014194766044616699,2.1957777061462402,, 5000,0.01904117874801159,0.01904117965698242,2.1625417394638062,, 5000,,,,2.1481730163097383,0.033409908413887024 5500,0.005845546722412109,0.005845546722412109,2.1757373745441435,, 6000,-0.02578740380704403,-0.02578740406036377,2.2073703379631042,, 6500,-0.006663489155471325,-0.006663490295410157,2.1882464270591737,, 7000,-0.02166476845741272,-0.021664767742156983,2.2032477045059204,, 7500,0.008638587780296803,0.008638587474822998,2.172944338798523,, 8000,0.011830026283860207,0.011830027103424073,2.169752900838852,, 8500,0.024285053834319115,0.02428505277633667,2.157297875881195,, 9000,0.00818329956382513,0.008183300495147705,2.173399622678757,, 9500,0.0668615847826004,0.06686158275604248,2.114721347332001,, 10000,0.057360075414180756,0.05736007666587829,2.1242228457927705,, 10000,,,,2.097888413667679,0.08369451016187668 10500,0.06884069740772247,0.0688406994342804,2.1127422280311583,, 11000,0.02789771370589733,0.02789771556854248,2.1536852095127106,, 11500,0.09138531237840652,0.09138531303405761,2.0901976108551024,, 12000,0.10403602570295334,0.10403602051734924,2.0775469059944154,, 12500,0.08804373443126678,0.08804372334480286,2.093539213895798,, 13000,0.13331347703933716,0.1333134868144989,2.0482694232463836,, 13500,0.10579406470060349,0.1057940742969513,2.075788856506348,, 14000,0.1302189975976944,0.13021900272369386,2.051363911628723,, 14500,0.14101365208625793,0.1410136513710022,2.040569269657135,, 15000,0.08936165273189545,0.08936165833473206,2.0922212710380554,, 15000,,,,1.8774564373493194,0.304126501083374 15500,0.0895434096455574,0.08954341077804566,2.092039510965347,, 16000,0.021286876872181892,0.021286877155303956,2.160296056509018,, 16500,0.08324971050024033,0.08324971103668213,2.098333217382431,, 17000,0.11891013383865356,0.11891013669967651,2.062672791004181,, 17500,0.13359619677066803,0.1335961949825287,2.0479867279529573,, 18000,0.12700319290161133,0.12700318574905395,2.054579733133316,, 18500,0.16050726175308228,0.1605072796344757,2.0210756483078005,, 19000,0.11986298859119415,0.11986299753189086,2.0617199251651765,, 19500,0.18126916885375977,0.1812691767215729,2.000313750743866,, 20000,0.18594513833522797,0.1859451537132263,1.9956377680301667,, 20000,,,,1.8686068803071976,0.31297603249549866 20500,0.15597958862781525,0.15597958087921143,2.0256033458709717,, 21000,0.1916520595550537,0.19165206623077394,1.9899308605194093,, 21500,0.1818467378616333,0.18184674453735353,1.9997361936569213,, 22000,0.1905975043773651,0.1905975136756897,1.9909854114055634,, 22500,0.1405470371246338,0.14054704189300538,2.0410358879566193,, 23000,0.21267107129096985,0.21267105317115784,1.968911864042282,, 23500,0.1852109283208847,0.18521092104911804,1.996372008562088,, 24000,0.18475738167762756,0.18475737261772157,1.9968255643844603,, 24500,0.19879989326000214,0.1987998914718628,1.982783041715622,, 25000,0.22323256731033325,0.22323257732391358,1.9583503544330596,, 25000,,,,1.8338491117954254,0.3477337956428528 25500,0.22924970090389252,0.22924968600273132,1.9523332455158233,, 26000,0.22784361243247986,0.22784361505508424,1.9537393190860748,, 26500,0.21676860749721527,0.2167686059474945,1.9648143317699431,, 27000,0.1593806892633438,0.15938069558143617,2.022202234506607,, 27500,0.18888811767101288,0.1888881220817566,1.9926947934627532,, 28000,0.17867620289325714,0.17867620348930358,2.0029067261219025,, 28500,0.19584621489048004,0.19584622168540955,1.985736694574356,, 29000,0.18205171823501587,0.18205172967910765,1.9995312101840972,, 29500,0.20991070568561554,0.2099106981754303,1.9716722218990326,, 30000,0.166031613945961,0.16603161525726318,2.0155513136386873,, 30000,,,,1.8590470081567765,0.322535902261734 30500,0.19970406591892242,0.19970405888557435,1.98187886428833,, 31000,0.2315494418144226,0.23154943919181822,1.9500334920883178,, 31500,0.22102193534374237,0.22102192211151123,1.9605610048770905,, 32000,0.23556064069271088,0.2355606198310852,1.946022305727005,, 32500,0.22610223293304443,0.22610224103927612,1.9554806892871857,, 33000,0.2338980883359909,0.23389808917045593,1.9476848378181457,, 33500,0.2303069829940796,0.23030698490142823,1.9512759561538697,, 34000,0.20536114275455475,0.20536115288734436,1.9762217633724213,, 34500,0.238141268491745,0.238141277551651,1.943441642999649,, 35000,0.19898933172225952,0.19898933744430541,1.9825935895442963,, 35000,,,,1.8403058993816375,0.34127700328826904 35500,0.20283499360084534,0.2028350086212158,1.9787479271888733,, 36000,0.18234245479106903,0.1823424563407898,1.9992404680252076,, 36500,0.19815360009670258,0.19815361189842223,1.9834293143749238,, 37000,0.23277856409549713,0.2327785701751709,1.9488043575286864,, 37500,0.2118435949087143,0.21184361171722413,1.969739307165146,, 38000,0.19836951792240143,0.19836953949928285,1.9832133975028992,, 38500,0.2093891203403473,0.20938913536071777,1.9721937882900238,, 39000,0.19542239606380463,0.19542239141464232,1.9861605288982391,, 39500,0.1940208375453949,0.19402081966400148,1.9875621078014374,, 40000,0.1852363497018814,0.18523633670806885,1.996346591234207,, 40000,,,,1.800716791152954,0.380866140127182 40500,0.1866176277399063,0.18661761355400086,1.994965318441391,, 41000,0.185668483376503,0.18566848945617676,1.9959144315719604,, 41500,0.19251126050949097,0.19251125502586364,1.989071682214737,, 42000,0.18013466894626617,0.18013468408584596,2.0014482305049897,, 42500,0.18430715799331665,0.18430715322494506,1.9972757818698883,, 43000,0.1435137391090393,0.14351374077796936,2.038069188117981,, 43500,0.2033105194568634,0.20331051993370056,1.9782724118232726,, 44000,0.20817968249320984,0.20817968583106994,1.9734032518863678,, 44500,0.21687616407871246,0.2168761546611786,1.9647067737579347,, 45000,0.19658063352108002,0.1965806143283844,1.985002319097519,, 45000,,,,1.8179256582260133,0.36365726590156555 45500,0.20966705679893494,0.20966703510284423,1.971915880203247,, 46000,0.18730169534683228,0.18730170702934265,1.9942812123298645,, 46500,0.19382217526435852,0.19382215762138366,1.987760773897171,, 47000,0.22278591990470886,0.22278594374656677,1.9587969834804535,, 47500,0.22301596403121948,0.22301595544815064,1.9585669672489165,, 48000,0.23117610812187195,0.23117612409591676,1.9504068081378936,, 48500,0.23507076501846313,0.23507076692581177,1.9465121581554412,, 49000,0.21670731902122498,0.21670731854438782,1.9648756036758424,, 49500,0.2592141628265381,0.2592141625881195,1.922368763923645,, 50000,0.2537287175655365,0.25372872352600095,1.9278542079925538,, 50000,,,,1.8115031439065934,0.37007978558540344 50500,0.2584187686443329,0.25841876912117007,1.9231641564369202,, 51000,0.2644350826740265,0.26443511295318606,1.9171478066444396,,