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,Q/Mean,Q/Stdev,Q/Max,Q/Min
1,0.0,1.0,1117.0,1117.0,1117.0,1117.0,1.0,,,0.0,,,,,,,,,,,,,,,,,,,
2,205.0,0.0,1937.0,1937.0,820.0,1937.0,0.9991882000000176,-21.0,-21.0,0.0,,,,36.60464997756772,42.04124769391064,201.15611267089844,2.788020610809326,5.000000000000001e-05,6.776263578034403e-21,5e-05,5e-05,14.734329999999998,11.578652,83.24656999999999,3.6869566,,,,
3,413.0,0.0,2768.0,2768.0,831.0,2768.0,0.9983655100000356,-21.0,-21.0,0.0,,,,37.448825304324814,40.97555825854826,265.18701171875,2.7428863048553467,5.0000000000000016e-05,1.3552527156068802e-20,5e-05,5e-05,46.146587,37.73792,313.11514,12.797323,-0.02228271633396313,0.010482918460358506,-0.008034438502509147,-0.03863051085398183
4,667.0,0.0,3783.0,3783.0,1015.0,3783.0,0.9973606600000572,-20.0,-20.0,0.0,,,,35.222983159418185,33.638557732845605,134.39295959472656,3.3111674785614014,5.000000000000001e-05,6.776263578034403e-21,5e-05,5e-05,54.700793999999995,28.679327,185.94606000000002,25.897139000000003,-0.05276434649310735,0.013212184652596557,-0.03154730399168329,-0.06887179555138573
5,867.0,0.0,4585.0,4585.0,802.0,4585.0,0.9965666800000744,-21.0,-21.0,0.0,,,,33.36415538668633,33.794293936783085,170.81182861328125,3.2840056419372563,5.000000000000001e-05,6.776263578034403e-21,5e-05,5e-05,53.996002000000004,31.833138,239.36745,27.415855,-0.03878277134735982,0.010679782367249705,-0.01826882790250238,-0.05715514831594193