step,training/mean_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward
500,-0.06299148499965668,4.95891127204895,,
1000,-0.04026485234498978,4.936184652328492,,
1500,-0.021233398467302322,4.9171531934738155,,
2000,-0.04819805175065994,4.944117834091187,,
2500,-0.017987502738833427,4.913907302856446,,
3000,-0.00332821742631495,4.899248017311097,,
3500,0.0007718334090895951,4.895147966384887,,
4000,-0.02426849491894245,4.9201883106231685,,
4500,0.019408974796533585,4.87651082611084,,
5000,0.03956621140241623,4.856353597640991,,
5000,,,4.764576165676117,0.13134363412857056
5500,0.0035057736095041037,4.892414026260376,,
6000,0.07169273495674133,4.824227098464966,,
6500,0.04290087893605232,4.853018915176391,,
7000,0.08703272044658661,4.808887046813965,,
7500,0.06876586377620697,4.8271539077758785,,
8000,0.06767558306455612,4.8282442417144775,,
8500,0.1446382999420166,4.75128145313263,,
9000,0.17601700127124786,4.7199027509689335,,
9500,0.2190401256084442,4.676879692554474,,
10000,0.32418739795684814,4.571732742786407,,
10000,,,4.4804092574119565,0.4155105423927307
10500,0.30955106019973755,4.586368625164032,,
11000,0.382164865732193,4.513754975318909,,
11500,0.4509696960449219,4.444950036525726,,
12000,0.44369199872016907,4.452227607727051,,
12500,0.4426208734512329,4.453298926353455,,
13000,0.5166301727294922,4.379289329528809,,
13500,0.509620726108551,4.386299058437348,,
14000,0.5437424778938293,4.3521772160530094,,
14500,0.5143827199935913,4.381537157535553,,
15000,0.5128225088119507,4.383097219467163,,
15000,,,4.31450040102005,0.5814193987846374
15500,0.5032016634941101,4.392718185901642,,
16000,0.5057186484336853,4.390201119422913,,
16500,0.5176594853401184,4.378260040760041,,
17000,0.5979547500610352,4.297964847564697,,
17500,0.5435119271278381,4.352408032417298,,
18000,0.5704073905944824,4.32551219367981,,
18500,0.5458237528800964,4.350096044540405,,
19000,0.5473615527153015,4.348558527469635,,
19500,0.6222348809242249,4.273685015678406,,
20000,0.5351817011833191,4.3607381162643435,,
20000,,,4.213122248649597,0.6827975511550903
20500,0.5295490622520447,4.366370635986328,,
21000,0.6115573644638062,4.284362462997437,,
21500,0.58497554063797,4.31094446182251,,
22000,0.6533452272415161,4.242574604988098,,
22500,0.5732257962226868,4.322694231033325,,
23000,0.557647168636322,4.338272756099701,,
23500,0.4686400890350342,4.427279688835144,,
24000,0.6333629488945007,4.262556609153748,,
24500,0.5775946378707886,4.318324839115143,,
25000,0.6978199481964111,4.198099555492401,,
25000,,,4.2353126847743985,0.6606071150302887
25500,0.6793652772903442,4.216554612159729,,
26000,0.7075976133346558,4.188322515010833,,
26500,0.7039701342582703,4.191950144290924,,
27000,0.7078973054885864,4.188022740840912,,
27500,0.6443480849266052,4.251571664333343,,
28000,0.6421403288841248,4.253779514789581,,
28500,0.6643054485321045,4.231614396572113,,
29000,0.8024880290031433,4.0934317927360535,,
29500,0.6663324236869812,4.229587611675263,,
30000,0.7001875042915344,4.19573210811615,,
30000,,,4.1677233147621155,0.7281964850425721
30500,0.707547664642334,4.188372183322906,,
31000,0.7254011631011963,4.170518857002258,,
31500,0.6835523843765259,4.212367723464966,,
32000,0.7591708302497864,4.136749336719513,,
32500,0.7512070536613464,4.144713054656982,,
33000,0.7450736165046692,4.150846219539642,,
33500,0.7068374752998352,4.189081984996796,,
34000,0.6966388821601868,4.199281002521515,,
34500,0.6986822485923767,4.1972375831604,,
35000,0.7451315522193909,4.150788439750672,,
35000,,,4.266372765302658,0.6295470345020294
35500,0.674969494342804,4.220950390338897,,
36000,0.6902756094932556,4.205644143581391,,
36500,0.6706236004829407,4.225296713352203,,
37000,0.6715084314346313,4.224411350250244,,
37500,0.643039345741272,4.2528805236816405,,
38000,0.6169635057449341,4.278956053733825,,
38500,0.7229084968566895,4.173011179447174,,
39000,0.7016206979751587,4.19429934835434,,
39500,0.738874614238739,4.157045084476471,,
40000,0.6677693128585815,4.228150787353516,,
40000,,,4.1694828736782075,0.7264369261264801
40500,0.7448002696037292,4.151119835853577,,
41000,0.6097077131271362,4.2862119030952455,,
41500,0.7037060260772705,4.192213777542114,,
42000,0.667831301689148,4.2280885658264165,,
42500,0.7251386046409607,4.170780729293823,,
43000,0.7790599465370178,4.116860114097595,,
43500,0.7027794122695923,4.193140605926514,,
44000,0.743413507938385,4.152506375789643,,
44500,0.7379533052444458,4.157966495513916,,
45000,0.7900598049163818,4.105860418319702,,
45000,,,4.086572549343109,0.8093472504615784
45500,0.6794936656951904,4.2164257941246035,,
46000,0.7674233317375183,4.128496903896332,,
46500,0.7528743743896484,4.1430451126098635,,
47000,0.7065930962562561,4.189326714038849,,
47500,0.6981306672096252,4.197789090156555,,
48000,0.7122209668159485,4.183698821544647,,
48500,0.7482271790504456,4.147692574024201,,
49000,0.7548724412918091,4.141047307491302,,
49500,0.8962744474411011,3.9996454238891603,,
50000,0.8232787847518921,4.072640985012055,,
50000,,,4.167422852516174,0.7284969472885132