step,training/mean_reward,training/mean_global_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward 500,0.09883884340524673,0.0988388442993164,2.585094175338745,, 1000,0.31514814496040344,0.3151481204032898,2.3687848992347718,, 1500,0.33801695704460144,0.3380170159339905,2.345916003704071,, 2000,0.38077467679977417,0.3807747039794922,2.3031583156585693,, 2500,0.3784728944301605,0.3784729166030884,2.305460103034973,, 3000,0.3847574293613434,0.38475741815567016,2.2991756014823914,, 3500,0.3974042236804962,0.39740422868728636,2.286528790950775,, 4000,0.4110168516635895,0.4110168652534485,2.272916154384613,, 4500,0.4114917516708374,0.4114917583465576,2.2724412612915037,, 5000,0.4106045365333557,0.41060451984405516,2.2733284997940064,, 5000,,,,2.2744255661964417,0.4095074534416199 5500,0.42030635476112366,0.4203063464164734,2.263626673221588,, 6000,0.415286660194397,0.415286648273468,2.2686463713645937,, 6500,0.41055455803871155,0.4105545616149902,2.273378458023071,, 7000,0.4037080407142639,0.4037080507278442,2.2802249689102174,, 7500,0.42395445704460144,0.42395447397232056,2.259978545665741,, 8000,0.43119844794273376,0.43119848823547363,2.252734531402588,, 8500,0.4119945168495178,0.4119944944381714,2.2719385251998903,, 9000,0.4096094071865082,0.40960938930511476,2.2743236303329466,, 9500,0.3941054046154022,0.39410541534423826,2.2898276042938233,, 10000,0.39230266213417053,0.39230269384384153,2.29163032579422,, 10000,,,,2.2967470610141754,0.3871859908103943 10500,0.3908345401287079,0.39083454418182373,2.2930984754562376,, 11000,0.3723529577255249,0.37235297536849976,2.311580044269562,, 11500,0.3703734874725342,0.37037346839904783,2.3135595512390137,, 12000,0.39386749267578125,0.3938675022125244,2.2900655174255373,, 12500,0.38508328795433044,0.38508330392837525,2.2988497157096863,, 13000,0.38810205459594727,0.3881020317077637,2.295830987930298,, 13500,0.3790167272090912,0.3790166926383972,2.304916326999664,, 14000,0.39240747690200806,0.39240752696990966,2.2915254926681516,, 14500,0.3993660807609558,0.39936610651016236,2.2845669131278994,, 15000,0.4016115367412567,0.40161154794692994,2.2823214716911315,, 15000,,,,2.3128393161296845,0.3710936903953552 15500,0.38930046558380127,0.38930046606063845,2.294632553577423,, 16000,0.3958090841770172,0.39580912685394287,2.2881238927841188,, 16500,0.3815975487232208,0.3815975503921509,2.302335469245911,, 17000,0.3898243010044098,0.38982433938980104,2.2941086802482604,, 17500,0.40535253286361694,0.4053525538444519,2.2785804657936097,, 18000,0.3477639853954315,0.34776399469375613,2.3361690249443052,, 18500,0.36096417903900146,0.3609641675949097,2.322968852043152,, 19000,0.36969780921936035,0.36969781970977783,2.3142351999282837,, 19500,0.3604229688644409,0.36042299032211306,2.3235100293159485,, 20000,0.3453044593334198,0.3453044781684875,2.338628541469574,, 20000,,,,2.325555741786957,0.35837727785110474 20500,0.39089685678482056,0.39089686822891234,2.293036151409149,, 21000,0.4304860234260559,0.43048596334457395,2.2534470562934876,, 21500,0.42426207661628723,0.42426207542419436,2.2596709442138674,, 22000,0.38556018471717834,0.3855601763725281,2.2983728432655335,, 22500,0.40029409527778625,0.4002940945625305,2.283638925075531,, 23000,0.4676303565502167,0.4676303882598877,2.216302631378174,, 23500,0.3802143633365631,0.38021436929702757,2.303718650341034,, 24000,0.38708698749542236,0.38708698987960816,2.2968460297584534,, 24500,0.38168323040008545,0.3816832542419434,2.3022497653961183,, 25000,0.352658212184906,0.35265819263458253,2.331274827003479,, 25000,,,,2.264131404161453,0.41980162262916565 25500,0.37030816078186035,0.3703081521987915,2.31362486743927,, 26000,0.37340614199638367,0.37340612411499025,2.310526895523071,, 26500,0.3665284514427185,0.3665284695625305,2.317404550075531,, 27000,0.3480551242828369,0.3480551266670227,2.335877892971039,, 27500,0.3381863236427307,0.3381863284111023,2.3457466912269593,, 28000,0.33318424224853516,0.3331842279434204,2.3507487916946412,, 28500,0.34999334812164307,0.34999338817596437,2.3339396314620973,, 29000,0.3612307012081146,0.36123069190979,2.3227023277282717,, 29500,0.3560679852962494,0.35606797409057617,2.3278650455474854,, 30000,0.3487584888935089,0.3487584753036499,2.3351745443344116,, 30000,,,,2.3420548593997954,0.341878205537796 30500,0.3242737352848053,0.32427372121810916,2.3596592984199525,, 31000,0.3269742429256439,0.3269742169380188,2.3569588027000425,, 31500,0.331946462392807,0.33194647884368894,2.3519865407943725,, 32000,0.3538981080055237,0.3538981385231018,2.3300348811149596,, 32500,0.3361845910549164,0.3361846041679382,2.3477484154701234,, 33000,0.3243791460990906,0.32437916040420534,2.359553859233856,, 33500,0.35682880878448486,0.356828773021698,2.3271042466163636,, 34000,0.34993278980255127,0.349932758808136,2.3340002608299257,, 34500,0.31978052854537964,0.3197805066108704,2.364152513027191,, 35000,0.3265296518802643,0.3265296669006348,2.357403352737427,, 35000,,,,2.305757747888565,0.3781752586364746 35500,0.33830732107162476,0.3383073091506958,2.345625710487366,, 36000,0.34578052163124084,0.34578050184249876,2.338152517795563,, 36500,0.33739808201789856,0.33739806747436524,2.3465349521636965,, 37000,0.31067517399787903,0.31067513799667357,2.373257881641388,, 37500,0.2901448607444763,0.29014485216140745,2.393788167476654,, 38000,0.3599267601966858,0.3599267597198486,2.324006259918213,, 38500,0.3697894811630249,0.3697894673347473,2.3141435523033143,, 39000,0.3895874619483948,0.389587450504303,2.2943455691337586,, 39500,0.4314839243888855,0.43148394107818605,2.2524490785598754,, 40000,0.3809228539466858,0.3809228916168213,2.3030101280212403,, 40000,,,,2.2743191039562225,0.4096139073371887 40500,0.4257664978504181,0.4257664966583252,2.2581665229797365,, 41000,0.4169514775276184,0.416951473236084,2.2669815464019774,, 41500,0.414630651473999,0.41463064098358154,2.26930237865448,, 42000,0.3985764980316162,0.3985765051841736,2.285356514453888,, 42500,0.4142265021800995,0.4142265286445618,2.2697064909935,, 43000,0.4133087992668152,0.4133087916374207,2.270624228000641,, 43500,0.4190700650215149,0.4190701112747192,2.2648629083633423,, 44000,0.40073639154434204,0.4007364230155945,2.283196596622467,, 44500,0.40611475706100464,0.40611470651626586,2.2778183131217955,, 45000,0.4028867483139038,0.4028867521286011,2.2810462675094603,, 45000,,,,2.309482082128525,0.3744509220123291 45500,0.40599700808525085,0.40599701738357546,2.277936002254486,, 46000,0.38081908226013184,0.3808190999031067,2.303113919734955,, 46500,0.4154774844646454,0.4154774484634399,2.2684555711746217,, 47000,0.3886411190032959,0.38864110565185545,2.295291913986206,, 47500,0.3956488072872162,0.39564878702163697,2.2882842326164248,, 48000,0.3834753632545471,0.38347538805007936,2.300457631587982,, 48500,0.34946689009666443,0.349466863155365,2.3344661564826965,, 49000,0.3620041310787201,0.36200413274765014,2.3219288868904115,, 49500,0.374152272939682,0.37415228128433226,2.309780738353729,, 50000,0.4014316499233246,0.40143164539337156,2.28250137424469,, 50000,,,,2.2749226665496827,0.4090103507041931