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
1,0.0,1.0,478.0,478.0,478.0,478.0,1.0,,,0.0,,,,,,,,,,,,,,,,0.8983135579407482,0.9883070480354864,4.998577182999947,0.0,,,,
2,0.0,1.0,956.0,956.0,478.0,956.0,1.0,,,0.0,,,,,,,,,,,,,,,,0.5556227853017673,0.8997466572364776,3.6930440629040366,0.0,,,,
3,0.0,1.0,1434.0,1434.0,478.0,1434.0,1.0,,,0.0,,,,,,,,,,,,,,,,0.4880512587305408,1.2184315272991455,7.981622766961119,0.0,,,,
4,120.0,0.0,1912.0,1912.0,478.0,1912.0,0.9995698000000142,9.0,9.0,0.0,,,,0.009689851886287215,0.012757843524910169,0.07483358681201935,8.608748612459749e-05,0.00010000000000000003,2.7105054312137605e-20,0.0001,0.0001,0.062028848,0.038314,0.20554277,0.0071169026,0.5300200921798093,0.9662463591142564,6.5978001830226605,0.0,,,,
5,239.0,0.0,2390.0,2390.0,478.0,2390.0,0.9991396000000284,9.0,9.0,0.0,,,,0.00922453978664864,0.01264670765167686,0.05902014672756195,0.0001334039407083765,0.0001,1.3552527156068802e-20,0.0001,0.0001,0.067527555,0.042208317999999995,0.24960242,0.011927829,0.8217024339343054,0.9620331221605151,5.227525088445949,0.0,,,,
6,359.0,0.0,2868.0,2868.0,478.0,2868.0,0.9987094000000424,9.0,9.0,0.0,,,,0.009785913288457477,0.01135032046581406,0.04819483682513237,0.0002595906553324312,0.00010000000000000003,2.7105054312137605e-20,0.0001,0.0001,0.07394858,0.041478443999999996,0.19334313,0.01290816,1.016981481614472,1.230148514321286,5.0096655797309415,0.0,,,,
7,478.0,0.0,3346.0,3346.0,478.0,3346.0,0.9982792000000568,12.0,12.0,0.0,,,,0.006171494484522005,0.008621506455658536,0.04043177887797356,0.00014119730622041968,0.0001,1.3552527156068802e-20,0.0001,0.0001,0.057615485,0.039739773,0.21918385,0.007797438,1.4498607827770469,1.761905543060363,5.277624938631289,0.0,,,,
8,598.0,0.0,3824.0,3824.0,478.0,3824.0,0.9978490000000708,3.0,3.0,0.0,,,,0.0093270375176265,0.010865469313652756,0.044152088463306434,0.00019287978648208082,0.00010000000000000003,2.7105054312137605e-20,0.0001,0.0001,0.07268587,0.044536818,0.21599004,0.011831168000000001,0.2135882596755921,0.36137271310460906,2.1020603780226303,0.0,,,,
9,717.0,0.0,4302.0,4302.0,478.0,4302.0,0.997418800000085,8.0,8.0,0.0,,,,0.007293934819504752,0.008668179302989909,0.042650774121284485,0.00018305983394384384,0.0001,1.3552527156068802e-20,0.0001,0.0001,0.0654777,0.039301243,0.20190288,0.011749206000000002,0.5106683851193774,1.121313650225975,5.72916711150828,0.0,0.038647518,0.018493647,0.085213184,-0.00357599
10,837.0,0.0,4780.0,4780.0,478.0,4780.0,0.9969886000000991,5.0,5.0,0.0,,,,0.006626958637813611,0.007690525022001264,0.042473964393138885,0.00013746884360443798,0.00010000000000000003,2.7105054312137605e-20,0.0001,0.0001,0.061515365,0.03587848,0.1821926,0.012653646999999999,0.5892099563483264,0.4988523336071251,2.2961085753574486,0.0,,,,