step,training/mean_reward,training/mean_global_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward 500,-0.08718936145305634,-0.08718937540054321,2.531332902431488,, 1000,-0.06893639266490936,-0.06893639469146728,2.5130799322128294,, 1500,-0.07459289580583572,-0.07459290075302125,2.518736430644989,, 2000,-0.08313997089862823,-0.08313996934890747,2.5272835025787352,, 2500,-0.015701774507761,-0.01570177412033081,2.4598453125953674,, 3000,-0.007870500907301903,-0.007870500087738036,2.4520140295028687,, 3500,-0.014082022942602634,-0.014082023620605469,2.4582255554199217,, 4000,-0.020678043365478516,-0.020678043842315672,2.464821576118469,, 4500,0.03661041334271431,0.03661041164398193,2.407533118247986,, 5000,0.044864632189273834,0.044864631175994873,2.3992788944244383,, 5000,,,,2.2614228999614716,0.1827206313610077 5500,0.04949851706624031,0.04949851560592651,2.3946450061798097,, 6000,0.04210849851369858,0.042108497142791745,2.402035036087036,, 6500,0.06709150969982147,0.06709150362014771,2.3770520305633545,, 7000,0.06370829045772552,0.06370829248428345,2.380435248851776,, 7500,0.04797230660915375,0.04797231006622314,2.396171236038208,, 8000,0.04217931255698204,0.042179316997528075,2.4019642062187194,, 8500,0.08364790678024292,0.0836479058265686,2.360495626449585,, 9000,0.08019349724054337,0.08019350385665894,2.3639500160217284,, 9500,0.10082823038101196,0.10082823228836059,2.343315299034119,, 10000,0.08412955701351166,0.08412955522537231,2.3600139708518983,, 10000,,,,2.201077628135681,0.24306590855121613 10500,0.08029162883758545,0.08029163074493408,2.363851898193359,, 11000,0.09334848076105118,0.09334848213195801,2.3507950472831727,, 11500,0.082823745906353,0.08282374238967896,2.36131978559494,, 12000,0.08509987592697144,0.08509987545013428,2.359043652534485,, 12500,0.09397520124912262,0.09397519874572755,2.3501683349609377,, 13000,0.10287211835384369,0.10287211179733276,2.3412714219093322,, 13500,0.11223634332418442,0.11223634958267212,2.3319071855545044,, 14000,0.11576959490776062,0.1157695951461792,2.32837393283844,, 14500,0.11058337241411209,0.1105833764076233,2.3335601658821106,, 15000,0.13095873594284058,0.13095873308181763,2.31318480014801,, 15000,,,,2.1263995957374573,0.3177439570426941 15500,0.11142433434724808,0.11142433738708496,2.332719199180603,, 16000,0.136672243475914,0.13667224407196044,2.3074712839126588,, 16500,0.11870156973600388,0.11870156192779541,2.3254419693946837,, 17000,0.13444459438323975,0.13444458770751952,2.309698947429657,, 17500,0.14305947721004486,0.14305947637557984,2.301084056377411,, 18000,0.1309906244277954,0.13099062395095826,2.3131528978347777,, 18500,0.13157427310943604,0.131574285030365,2.312569250583649,, 19000,0.10900072753429413,0.10900072956085205,2.3351428108215333,, 19500,0.11670161783695221,0.11670161437988281,2.327441906929016,, 20000,0.11961931735277176,0.11961932039260864,2.324524211406708,, 20000,,,,2.1615434789657595,0.2826000452041626 20500,0.12919247150421143,0.12919246530532838,2.3149510765075685,, 21000,0.1263352334499359,0.1263352255821228,2.317808306694031,, 21500,0.13126717507839203,0.13126718282699584,2.3128763604164124,, 22000,0.13859374821186066,0.13859375524520873,2.3055497727394103,, 22500,0.126836895942688,0.1268368992805481,2.317306626319885,, 23000,0.1357792615890503,0.13577926826477052,2.308364264011383,, 23500,0.13915003836154938,0.13915003967285156,2.304993505001068,, 24000,0.12331124395132065,0.12331124687194825,2.320832284927368,, 24500,0.12842729687690735,0.1284272904396057,2.3157162427902223,, 25000,0.13625536859035492,0.13625538444519042,2.307888153553009,, 25000,,,,2.1204052031040193,0.32373830676078796 25500,0.13288365304470062,0.13288366031646728,2.3112598729133604,, 26000,0.1306069940328598,0.13060698699951173,2.3135365552902223,, 26500,0.13904881477355957,0.139048819065094,2.3050947041511534,, 27000,0.14465457201004028,0.14465456533432006,2.2994889597892763,, 27500,0.12552373111248016,0.12552373504638673,2.3186198048591615,, 28000,0.1469792127609253,0.14697921419143678,2.2971643195152285,, 28500,0.13935570418834686,0.13935570430755614,2.304787823200226,, 29000,0.15816302597522736,0.15816302061080934,2.2859805059432983,, 29500,0.17586636543273926,0.17586635541915893,2.268277184486389,, 30000,0.16847540438175201,0.1684753918647766,2.2756681489944457,, 30000,,,,2.067536563873291,0.3766070008277893 30500,0.16832952201366425,0.16832952976226806,2.275814007282257,, 31000,0.14743781089782715,0.14743781566619873,2.296705711364746,, 31500,0.16313040256500244,0.16313041114807128,2.281013126373291,, 32000,0.16540180146694183,0.16540180158615111,2.278741735935211,, 32500,0.16001944243907928,0.1600194458961487,2.2841240854263307,, 33000,0.16679386794567108,0.1667938709259033,2.2773496518135072,, 33500,0.16540804505348206,0.16540803718566893,2.27873549079895,, 34000,0.15513759851455688,0.15513758850097656,2.2890059509277343,, 34500,0.15555039048194885,0.15555037641525268,2.2885931487083435,, 35000,0.1545112133026123,0.15451122188568114,2.2896323113441466,, 35000,,,,2.12775252699852,0.3163909614086151 35500,0.14927862584590912,0.14927864360809326,2.294864893436432,, 36000,0.14519813656806946,0.1451981415748596,2.298945384502411,, 36500,0.1189863458275795,0.11898634767532348,2.3251571798324586,, 37000,0.1512337177991867,0.15123371744155883,2.292909821033478,, 37500,0.15562014281749725,0.1556201539039612,2.288523379325867,, 38000,0.14101558923721313,0.14101559638977051,2.303127939224243,, 38500,0.1393895000219345,0.13938948345184327,2.3047540545463563,, 39000,0.15904390811920166,0.15904391717910765,2.285099603176117,, 39500,0.14030230045318604,0.1403023142814636,2.3038412289619448,, 40000,0.1628817468881607,0.16288173580169676,2.2812618050575257,, 40000,,,,2.1071667540073395,0.3369767665863037 40500,0.1495496779680252,0.1495497031211853,2.294593846321106,, 41000,0.14722241461277008,0.14722240734100342,2.296921124458313,, 41500,0.15795406699180603,0.1579540638923645,2.286189458847046,, 42000,0.14894624054431915,0.14894625520706176,2.2951972827911375,, 42500,0.16007807850837708,0.16007806301116945,2.2840654735565185,, 43000,0.14689065515995026,0.1468906464576721,2.29725288105011,, 43500,0.156832754611969,0.15683273983001708,2.2873107929229737,, 44000,0.16935870051383972,0.1693587098121643,2.2747848315238954,, 44500,0.16625003516674042,0.16625002527236937,2.277893501281738,, 45000,0.1549280434846878,0.15492804336547852,2.289215491771698,, 45000,,,,2.119650950431824,0.32449257373809814 45500,0.16541045904159546,0.16541046380996705,2.278733060836792,, 46000,0.15617205202579498,0.15617207098007202,2.2879714612960815,, 46500,0.170013427734375,0.17001342964172364,2.2741301078796385,, 47000,0.1541394740343094,0.15413949155807496,2.2900040440559386,, 47500,0.1670684963464737,0.16706850481033325,2.2770750427246096,, 48000,0.1701829582452774,0.17018295669555664,2.273960580825806,, 48500,0.1675613969564438,0.167561402797699,2.2765821194648743,, 49000,0.14955788850784302,0.14955788040161133,2.294585659980774,, 49500,0.17626681923866272,0.1762668299674988,2.2678766984939576,, 50000,0.16646689176559448,0.16646689510345458,2.2776766419410706,, 50000,,,,2.079480013847351,0.3646634817123413 50500,0.18186846375465393,0.1818684720993042,2.262275061607361,, 51000,0.19198085367679596,0.19198085069656373,2.2521626753807067,,