| step,training/mean_reward,training/mean_nusselt,evaluation/mean_nusselt,evaluation/mean_reward |
| 500,-0.08490888774394989,4.980828685760498,, |
| 1000,-0.0878649428486824,4.983784786224366,, |
| 1500,-0.07708005607128143,4.972999826431274,, |
| 2000,-0.07105544954538345,4.966975282669067,, |
| 2500,-0.06446612626314163,4.960385907649994,, |
| 3000,-0.03681410849094391,4.932733913421631,, |
| 3500,-0.04249918460845947,4.938418998718261,, |
| 4000,-0.08245683461427689,4.978376658439636,, |
| 4500,-0.019789254292845726,4.91570904827118,, |
| 5000,0.006478671915829182,4.8894411277771,, |
| 5000,,,4.782105293273926,0.11381450653076172 |
| 5500,-0.017507405951619148,4.913427208900452,, |
| 6000,-0.04208756983280182,4.938007356643677,, |
| 6500,0.044804394245147705,4.85111540555954,, |
| 7000,0.03831161931157112,4.857608160495758,, |
| 7500,0.03597576916217804,4.8599440431594845,, |
| 8000,0.03191151097416878,4.864008289337158,, |
| 8500,0.09379095584154129,4.802128845691681,, |
| 9000,0.07521641999483109,4.820703365802765,, |
| 9500,0.059910960495471954,4.836008848190308,, |
| 10000,0.1105252206325531,4.78539455652237,, |
| 10000,,,4.684951794147492,0.21096800565719603 |
| 10500,0.08609014749526978,4.809829604625702,, |
| 11000,0.10020294040441513,4.795716833114624,, |
| 11500,0.07968094199895859,4.816238836288452,, |
| 12000,0.10782557725906372,4.788094236850738,, |
| 12500,0.11555590480566025,4.780363923549652,, |
| 13000,0.12862764298915863,4.767292178630829,, |
| 13500,0.1787448674440384,4.717174905300141,, |
| 14000,0.14618641138076782,4.749733354568481,, |
| 14500,0.14544577896595,4.75047395324707,, |
| 15000,0.15179164707660675,4.744128173351288,, |
| 15000,,,4.513633179664612,0.3822866201400757 |
| 15500,0.15027223527431488,4.74564752626419,, |
| 16000,0.17486625909805298,4.721053531169892,, |
| 16500,0.16517868638038635,4.730741195678711,, |
| 17000,0.19309936463832855,4.7028204622268674,, |
| 17500,0.1813145875930786,4.714605164527893,, |
| 18000,0.21861980855464935,4.677299888134002,, |
| 18500,0.1758539229631424,4.720065884590149,, |
| 19000,0.23255319893360138,4.663366681098938,, |
| 19500,0.21325437724590302,4.68266543006897,, |
| 20000,0.22737358510494232,4.6685462183952335,, |
| 20000,,,4.470651566982269,0.4252682328224182 |
| 20500,0.263619601726532,4.632300042629242,, |
| 21000,0.24875690042972565,4.6471630544662474,, |
| 21500,0.29425114393234253,4.601668506145478,, |
| 22000,0.26813945174217224,4.627780330181122,, |
| 22500,0.2336183488368988,4.662301451683044,, |
| 23000,0.30845963954925537,4.587460469722748,, |
| 23500,0.30904877185821533,4.586871285915374,, |
| 24000,0.3005214333534241,4.595398387432098,, |
| 24500,0.27308303117752075,4.622836617946625,, |
| 25000,0.3056974411010742,4.590222301959991,, |
| 25000,,,4.315398707389831,0.5805210924148559 |
| 25500,0.2851932644844055,4.610726454257965,, |
| 26000,0.3070009648799896,4.588918898582459,, |
| 26500,0.2682599723339081,4.627659863471985,, |
| 27000,0.3591163158416748,4.536803454875946,, |
| 27500,0.3893619775772095,4.506557786941529,, |
| 28000,0.31175851821899414,4.584161316394806,, |
| 28500,0.29586562514305115,4.600054039478302,, |
| 29000,0.3479352593421936,4.5479842801094055,, |
| 29500,0.32951560616493225,4.566404173851013,, |
| 30000,0.37990429997444153,4.516015627384186,, |
| 30000,,,4.246590051651001,0.6493297481536865 |
| 30500,0.3652186095714569,4.530701138019562,, |
| 31000,0.34288477897644043,4.553035095691681,, |
| 31500,0.44933560490608215,4.446584166049957,, |
| 32000,0.4329663813114166,4.46295353269577,, |
| 32500,0.3943996727466583,4.50152028799057,, |
| 33000,0.4277005195617676,4.468219334125519,, |
| 33500,0.48550719022750854,4.410412717819214,, |
| 34000,0.43721821904182434,4.4587015099525455,, |
| 34500,0.41324540972709656,4.4826743793487545,, |
| 35000,0.40108922123908997,4.494830593585968,, |
| 35000,,,4.19390767455101,0.7020121252536774 |
| 35500,0.4222796559333801,4.4736401519775395,, |
| 36000,0.4581157863140106,4.4378041462898254,, |
| 36500,0.435651034116745,4.460268796443939,, |
| 37000,0.5605266094207764,4.335393747329712,, |
| 37500,0.48858222365379333,4.407337341308594,, |
| 38000,0.43420907855033875,4.461710805416107,, |
| 38500,0.4914892017841339,4.4044305572509765,, |
| 39000,0.4449007213115692,4.451019083499909,, |
| 39500,0.44721701741218567,4.448702753543854,, |
| 40000,0.5111424326896667,4.384777391910553,, |
| 40000,,,4.148989750146866,0.7469300496578216 |
| 40500,0.5653572678565979,4.330562698364258,, |
| 41000,0.5657103061676025,4.330209637641906,, |
| 41500,0.5113364458084106,4.3845835819244385,, |
| 42000,0.5443275570869446,4.351592366218567,, |
| 42500,0.5323209762573242,4.363598475456238,, |
| 43000,0.4727969169616699,4.423123106479645,, |
| 43500,0.46365898847579956,4.432260662555694,, |
| 44000,0.6025660037994385,4.293353728771209,, |
| 44500,0.48070549964904785,4.415214454174042,, |
| 45000,0.5672982931137085,4.328621855735779,, |
| 45000,,,4.078591849803924,0.817327950000763 |
| 45500,0.6120277047157288,4.283892143726349,, |
| 46000,0.6059440970420837,4.289975656032563,, |
| 46500,0.5989245176315308,4.296995299339295,, |
| 47000,0.5509999990463257,4.344919733524322,, |
| 47500,0.5875324010848999,4.3083873538970945,, |
| 48000,0.6509262323379517,4.244993340969086,, |
| 48500,0.5197104215621948,4.376209565162659,, |
| 49000,0.6163337826728821,4.279585714817047,, |
| 49500,0.581639289855957,4.314280577659607,, |
| 50000,0.5903351306915283,4.305584682941436,, |
| 50000,,,4.012059004306793,0.8838607954978943 |
| 50500,0.5699482560157776,4.325971701145172,, |
| 51000,0.6723026037216187,4.223616890907287,, |
|
|