Episode #,Training Iter,In Heatup,ER #Transitions,ER #Episodes,Episode Length,Total steps,Epsilon,Shaped Training Reward,Training Reward,Update Target Network,Evaluation Reward,Shaped Evaluation Reward,Success Rate,Loss/Mean,Loss/Stdev,Loss/Max,Loss/Min,Learning Rate/Mean,Learning Rate/Stdev,Learning Rate/Max,Learning Rate/Min,Grads (unclipped)/Mean,Grads (unclipped)/Stdev,Grads (unclipped)/Max,Grads (unclipped)/Min,Discounted Return/Mean,Discounted Return/Stdev,Discounted Return/Max,Discounted Return/Min,Q/Mean,Q/Stdev,Q/Max,Q/Min 1,0.0,1.0,486.0,486.0,486.0,486.0,1.0,,,0.0,,,,,,,,,,,,,,,,1.027285241237078,0.8961037725396955,3.502959469093688,0.0,,,, 2,0.0,1.0,573.0,573.0,87.0,573.0,1.0,,,0.0,,,,,,,,,,,,,,,,0.2991949731169189,0.4147830569909918,1.0,0.0,,,, 3,0.0,1.0,722.0,722.0,149.0,722.0,1.0,,,0.0,,,,,,,,,,,,,,,,1.089942054123867,0.6773639260883686,1.9560606270183023,0.0,,,, 4,0.0,1.0,1057.0,1057.0,335.0,1057.0,1.0,,,0.0,,,,,,,,,,,,,,,,1.6150170189100268,1.2171006279541683,4.3034191502088746,0.0,,,, 5,51.0,0.0,1260.0,1260.0,203.0,1260.0,0.9997990300000044,5.0,55.0,0.0,,,,3.9317352210774135,2.407134574195501e-05,3.931850671768189,3.931662797927856,0.00025,0.0,0.00025,0.00025,0.0016130212,0.0023544687,0.009832208,0.0007587225,1.5742518458459676,1.1031375801910266,3.252515696371334,0.0,,,, 6,70.0,0.0,1335.0,1335.0,75.0,1335.0,0.999724780000006,2.0,15.0,0.0,,,,3.9317221516057055,2.8393100704527187e-05,3.9317376613616943,3.931619882583618,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.0017485315,0.0025665222,0.0096031735,0.0007149652000000001,0.630055465573955,0.7534012288320482,1.886384871716129,0.0,,,, 7,91.0,0.0,1422.0,1422.0,87.0,1422.0,0.9996386500000078,1.0,15.0,0.0,,,,3.931710742768787,1.9757311614159746e-05,3.931730508804321,3.9316580295562735,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.0028334420000000003,0.0035875288000000003,0.009559939,0.0007086714,0.2731692938539037,0.40901966584690697,1.0,0.0,,,, 8,159.0,0.0,1693.0,1693.0,271.0,1693.0,0.9993703600000136,5.0,55.0,0.0,,,,3.9316638049794665,8.835770227381325e-05,3.931716203689575,3.931101083755493,0.00025,0.0,0.00025,0.00025,0.0016883161999999999,0.0027075324,0.013138678999999999,0.0006439898,1.3777471984624352,0.8115021837176055,3.11412900057984,0.0,,,, 9,201.0,0.0,1861.0,1861.0,168.0,1861.0,0.9992040400000172,3.0,50.0,0.0,,,,3.93158137230646,9.899681346698072e-05,3.931650400161743,3.931218385696411,0.00025,0.0,0.00025,0.00025,0.0017703464,0.002836768,0.009999716,0.0006297505000000001,0.9971291228971556,0.7740837108535874,2.18976824447548,0.0,,,, 10,279.0,0.0,2172.0,2172.0,311.0,2172.0,0.998896150000024,4.0,65.0,0.0,,,,3.9314247186367326,0.00020985691871384964,3.9315884113311768,3.930165529251098,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.0026259087,0.0040648757,0.01969288,0.0006104264,1.0234306140936356,0.5002579938176909,2.1008995427938943,0.0,,,, 11,406.0,0.0,2681.0,2681.0,509.0,2681.0,0.9983922400000348,9.0,320.0,0.0,,,,3.9312460666566382,0.00015088229763296552,3.931385040283203,3.930580139160156,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.001717266,0.0028960726,0.011583811000000001,0.00053362455,1.5487425802799972,0.9434112651663112,4.0430534797383535,0.0,0.02211338306466794,0.012693727271687969,0.04014564007520752,0.005227018147707514 12,471.0,0.0,2941.0,2941.0,260.0,2941.0,0.9981348400000404,7.0,110.0,0.0,,,,3.93098396888146,0.00025558325060157967,3.931251525878906,3.930067777633667,0.00025,0.0,0.00025,0.00025,0.0022192413,0.0035853293,0.01259266,0.00053927617,1.9247686125714616,1.4763974008694143,4.5174296147906645,0.0,,,, 13,506.0,0.0,3082.0,3082.0,141.0,3082.0,0.9979952500000436,0.0,0.0,0.0,,,,3.9310501030513216,9.928599760211657e-05,3.931129693984986,3.9304840564727774,0.00025,0.0,0.00025,0.00025,0.0010526914999999999,0.0018549723000000002,0.01182043,0.0005092583599999999,0.0,0.0,0.0,0.0,0.027007679268718384,0.015777484463216175,0.04155192077159939,-0.004159464687108204 14,569.0,0.0,3331.0,3331.0,249.0,3331.0,0.9977487400000488,7.0,110.0,0.0,,,,3.9310040550847214,0.00013713500875067318,3.931095123291016,3.930255889892578,0.00025,0.0,0.00025,0.00025,0.0014536895000000001,0.003044227,0.016551271,0.00046372807,2.0098751682981617,1.1093871734323564,4.000165956499947,0.0,,,, 15,655.0,0.0,3677.0,3677.0,346.0,3677.0,0.9974062000000564,0.0,0.0,0.0,,,,3.930485764215159,0.0004791675138463453,3.9310092926025386,3.9289395809173584,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.0036637257,0.005057025,0.018913887,0.00048042364999999996,0.0,0.0,0.0,0.0,0.02673329152166901,0.018246214309196592,0.0670881908386951,-0.0044445902109140345 16,674.0,0.0,3753.0,3753.0,76.0,3753.0,0.997330960000058,1.0,10.0,0.0,,,,3.9302756033445663,0.00026491583393688006,3.9304935932159424,3.9293212890625,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.0028473618,0.0038246207,0.013993822,0.0011612439,0.42667230386804816,0.4209997414589432,1.0,0.0,,,, 17,723.0,0.0,3948.0,3948.0,195.0,3948.0,0.997137910000062,0.0,0.0,0.0,,,,3.9301121332207503,0.0007249285851701791,3.93054461479187,3.926475524902344,0.00025,0.0,0.00025,0.00025,0.004166719,0.00607345,0.029815415,0.0009982587,0.0,0.0,0.0,0.0,,,, 18,754.0,0.0,4073.0,4073.0,125.0,4073.0,0.9970141600000648,2.0,15.0,0.0,,,,3.9299140130319903,0.0005883850513097767,3.930288553237915,3.928234100341797,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.0039398223,0.004844566,0.015578092,0.0014653493,0.4379218073475659,0.6904045765467619,1.886384871716129,0.0,0.024141461091737523,0.014920733127398141,0.0439044233411556,-0.0014312818646425587 19,831.0,0.0,4381.0,4381.0,308.0,4381.0,0.9967092400000714,4.0,90.0,0.0,,,,3.930125174584327,0.0005156776213968518,3.930519104003906,3.927454710006714,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.0027787187,0.0045149909999999994,0.028442059,0.0007121817,1.0691845626589795,0.8498240160885151,2.745451683091903,0.0,,,, 20,929.0,0.0,4773.0,4773.0,392.0,4773.0,0.99632116000008,7.0,100.0,0.0,,,,3.9303993935487718,0.000375229125029804,3.9306261539459233,3.9283268451690674,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.0022639388,0.00399352,0.019860761,0.000582562,1.4393231985989243,0.8717358172149811,3.0489377308973795,0.0,0.02399343630919913,0.013934502176120992,0.04786662720143856,0.004320444166660803 21,961.0,0.0,4902.0,4902.0,129.0,4902.0,0.9961934500000826,3.0,30.0,0.0,,,,3.93039171397686,0.00030082864829957884,3.930622816085816,3.9292621612548833,0.00025,0.0,0.00025,0.00025,0.0024432157999999997,0.004213264699999999,0.013954926999999999,0.00055390206,1.0833967298409597,0.9363232923629204,2.6221126076070793,0.0,,,, 22,992.0,0.0,5026.0,5026.0,124.0,5026.0,0.9960706900000852,4.0,80.0,0.0,,,,3.9303887446721393,0.0003660622821289879,3.930558443069458,3.928993225097656,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.0017878629000000002,0.0031582718,0.013690787,0.0005955570400000001,1.3451618537673,1.1096991653941397,3.0898896329640837,0.0,,,, 23,1112.0,0.0,5504.0,5504.0,478.0,5504.0,0.9955974700000956,7.0,110.0,0.0,,,,3.9300644317594897,0.00048261017522260256,3.93047833442688,3.927913665771485,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.0030386879,0.004634549,0.022174232000000002,0.00073956157,1.235612882603384,0.6420095750226174,3.0848770640447634,0.0,0.035258680271606266,0.011647875887269484,0.054692128300667435,0.016495494544506634 24,1156.0,0.0,5679.0,5679.0,175.0,5679.0,0.9954242200000992,2.0,25.0,0.0,,,,3.9298657449808982,0.0006624029423227996,3.93034553527832,3.927419424057007,0.00025,0.0,0.00025,0.00025,0.003681957,0.005591136,0.022265982,0.0007994298,0.8552780879101226,0.523480862790951,1.877521022998968,0.0,,,, 25,1180.0,0.0,5776.0,5776.0,97.0,5776.0,0.9953281900001014,2.0,45.0,0.0,,,,3.9299136300881705,0.00031610408354052963,3.9302179813385014,3.928537130355835,0.00025,0.0,0.00025,0.00025,0.0021914851,0.0028706120000000003,0.015887184,0.0010854277,0.7507546721376259,0.7004130331576832,1.8261686238355863,0.0,,,,