step,training/mean_reward,training/mean_global_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward 500,-0.07284899801015854,-0.07284899568557739,2.516992525100708,, 1000,-0.08247055858373642,-0.0824705605506897,2.526614098072052,, 1500,-0.081957146525383,-0.08195714282989502,2.5261006712913514,, 2000,-0.09400798380374908,-0.09400798463821411,2.538151517391205,, 2500,-0.03117496147751808,-0.031174960136413573,2.47531849193573,, 3000,-0.040552545338869095,-0.040552542686462405,2.4846960706710814,, 3500,-0.027283145114779472,-0.0272831449508667,2.471426689147949,, 4000,-0.02746737375855446,-0.027467374324798583,2.4716108980178833,, 4500,0.009480989538133144,0.009480987548828125,2.434662547111511,, 5000,0.01582098938524723,0.01582098913192749,2.4283225474357604,, 5000,,,,2.2840357506275177,0.1601077914237976 5500,0.009929155930876732,0.009929156303405762,2.434214381694794,, 6000,-0.00016683874127920717,-0.0001668386459350586,2.4443103799819945,, 6500,0.029412414878606796,0.029412415981292725,2.4147311053276064,, 7000,0.015340999700129032,0.015341001033782959,2.4288025283813477,, 7500,0.04828393831849098,0.04828394079208374,2.39585959148407,, 8000,0.027136696502566338,0.027136694431304932,2.417006841659546,, 8500,0.07230944186449051,0.0723094391822815,2.371834099292755,, 9000,0.048889052122831345,0.048889055728912355,2.39525447511673,, 9500,0.05876648798584938,0.05876648855209351,2.3853770394325258,, 10000,0.05273273587226868,0.05273273324966431,2.3914108033180237,, 10000,,,,2.2356233417987825,0.20852018892765045 10500,0.0887230858206749,0.08872308492660523,2.355420449256897,, 11000,0.08898043632507324,0.08898043489456177,2.3551631011962892,, 11500,0.08206947147846222,0.08206947517395019,2.3620740489959715,, 12000,0.0905391201376915,0.09053913021087646,2.3536044063568116,, 12500,0.10625230520963669,0.10625230598449707,2.337891225337982,, 13000,0.109677255153656,0.1096772484779358,2.334466288089752,, 13500,0.11173564195632935,0.11173565101623535,2.332407876491547,, 14000,0.09036831557750702,0.09036831712722779,2.3537752056121826,, 14500,0.1243913546204567,0.12439135694503785,2.319752179145813,, 15000,0.1234671100974083,0.12346712493896485,2.3206764101982116,, 15000,,,,2.1257523238658904,0.31839120388031006 15500,0.12805908918380737,0.12805908918380737,2.3160844388008117,, 16000,0.13696682453155518,0.1369668369293213,2.307176693916321,, 16500,0.13080060482025146,0.13080060958862305,2.313342926979065,, 17000,0.137887105345726,0.1378871202468872,2.306256417751312,, 17500,0.15704573690891266,0.15704573345184325,2.2870978031158447,, 18000,0.14428897202014923,0.14428897428512574,2.2998545632362366,, 18500,0.1392766237258911,0.1392766270637512,2.3048669080734254,, 19000,0.15581251680850983,0.15581250572204589,2.2883310408592226,, 19500,0.14729617536067963,0.14729618215560913,2.296847346305847,, 20000,0.14627820253372192,0.14627820062637328,2.2978653359413146,, 20000,,,,2.1434880673885344,0.3006554841995239 20500,0.15487876534461975,0.15487877368927003,2.289264750957489,, 21000,0.16191016137599945,0.16191016149520873,2.282233376979828,, 21500,0.16468729078769684,0.1646873049736023,2.2794562277793884,, 22000,0.16435864567756653,0.16435863161087036,2.2797848925590514,, 22500,0.1759740263223648,0.1759740309715271,2.268169508457184,, 23000,0.14877089858055115,0.14877091121673583,2.295372636318207,, 23500,0.1593804955482483,0.1593805079460144,2.2847630252838136,, 24000,0.14516723155975342,0.14516724014282226,2.298976301193237,, 24500,0.1500563621520996,0.15005637502670288,2.2940871591567995,, 25000,0.14823997020721436,0.14823997020721436,2.2959035658836364,, 25000,,,,2.130064435005188,0.3140791058540344 25500,0.15658481419086456,0.1565848045349121,2.2875587220191957,, 26000,0.1492302566766739,0.1492302703857422,2.2949132595062256,, 26500,0.17601348459720612,0.17601349353790283,2.268130049228668,, 27000,0.156053826212883,0.15605384588241578,2.2880896854400636,, 27500,0.17075638473033905,0.17075635385513305,2.2733871846199034,, 28000,0.12509135901927948,0.12509135055541992,2.31905219078064,, 28500,0.15504378080368042,0.15504377365112304,2.289099756717682,, 29000,0.155385822057724,0.15538580894470214,2.2887577252388,, 29500,0.17931413650512695,0.17931413507461547,2.264829409122467,, 30000,0.14405401051044464,0.14405400228500367,2.3000895295143127,, 30000,,,,2.108922697305679,0.3352208137512207 30500,0.1728549748659134,0.17285499954223632,2.271288526535034,, 31000,0.16838832199573517,0.1683883352279663,2.2757551975250245,, 31500,0.19653981924057007,0.19653982305526732,2.247603726387024,, 32000,0.16980622708797455,0.1698062391281128,2.2743372921943665,, 32500,0.1903025507926941,0.19030255270004273,2.253840987205505,, 33000,0.16106392443180084,0.16106392574310302,2.2830796155929565,, 33500,0.18171410262584686,0.18171411275863647,2.2624294199943544,, 34000,0.16792571544647217,0.16792572355270385,2.2762178149223327,, 34500,0.16000893712043762,0.16000893783569337,2.2841346116065977,, 35000,0.17219094932079315,0.1721909580230713,2.2719525790214536,, 35000,,,,2.105157878398895,0.3389856815338135 35500,0.17283929884433746,0.17283930397033692,2.2713042240142824,, 36000,0.18398155272006989,0.18398155641555786,2.260161968231201,, 36500,0.15513131022453308,0.15513133764266968,2.289012189865112,, 37000,0.16344286501407623,0.16344288635253906,2.280700644016266,, 37500,0.16775661706924438,0.16775661993026733,2.2763869104385375,, 38000,0.1437034010887146,0.1437033996582031,2.300440122127533,, 38500,0.19318921864032745,0.19318924617767333,2.2509542956352235,, 39000,0.18310870230197906,0.18310872077941895,2.261034816265106,, 39500,0.19639214873313904,0.19639215898513793,2.2477513699531557,, 40000,0.1735430210828781,0.17354302501678467,2.2706005129814146,, 40000,,,,2.1538765203952788,0.2902669906616211 40500,0.19081838428974152,0.19081839036941528,2.2533251333236692,, 41000,0.19824714958667755,0.19824715232849122,2.2458963828086853,, 41500,0.1705096811056137,0.17050966691970826,2.273633864879608,, 42000,0.19678214192390442,0.196782133102417,2.247361406326294,, 42500,0.17333373427391052,0.17333374214172365,2.2708097829818725,, 43000,0.1892850697040558,0.18928504657745363,2.254858489990234,, 43500,0.19315484166145325,0.19315485191345214,2.250988679885864,, 44000,0.17756743729114532,0.17756744718551637,2.266576090335846,, 44500,0.19930996000766754,0.19930998182296752,2.2448335528373717,, 45000,0.19340313971042633,0.19340316438674926,2.250740375995636,, 45000,,,,2.1233883452415467,0.3207551836967468 45500,0.20025090873241425,0.20025090503692627,2.2438926210403443,, 46000,0.19082942605018616,0.19082943630218505,2.2533141112327577,, 46500,0.19664253294467926,0.1966425232887268,2.2475010209083557,, 47000,0.18970148265361786,0.18970146465301513,2.2544420595169066,, 47500,0.17102493345737457,0.17102494335174562,2.273118592262268,, 48000,0.2168714851140976,0.21687149810791015,2.2272720403671267,, 48500,0.21920549869537354,0.21920550203323363,2.224938039779663,, 49000,0.21964401006698608,0.21964401769638062,2.2244995188713075,, 49500,0.2057390660047531,0.2057390580177307,2.2384044857025147,, 50000,0.2132531851530075,0.21325318336486818,2.2308903584480286,, 50000,,,,2.0895031124353407,0.3546404540538788 50500,0.19286243617534637,0.19286244964599608,2.251281086444855,, 51000,0.18694031238555908,0.18694031429290772,2.2572032160758972,,