1
0
mirror of https://github.com/gryf/coach.git synced 2026-01-25 00:35:46 +01:00
Files
coach/rl_coach/traces/Atari_NStepQ_pong/trace.csv
2018-10-02 17:55:16 +03:00

7 lines
1.9 KiB
CSV

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,Entropy/Mean,Entropy/Stdev,Entropy/Max,Entropy/Min,Q/Mean,Q/Stdev,Q/Max,Q/Min,Q Values/Mean,Q Values/Stdev,Q Values/Max,Q Values/Min,Value Loss/Mean,Value Loss/Stdev,Value Loss/Max,Value Loss/Min
1,0.0,1.0,1117.0,1.0,1117.0,1117.0,0.5,,,0.0,,,,,,,,,,,,,,,,-1.5180229894995567,0.6998808293377133,-0.08930329112720292,-3.148474706421977,,,,,,,,,,,,,,,,
2,151.0,0.0,760.0,1.0,760.0,1877.0,0.4925519999999968,-21.0,-21.0,0.0,,,,,,,,,,,,,,,,-2.5205372468300253,0.5838419974113738,-0.7105532272722921,-3.3699982440767453,,,,,,,,,0.07112427,0.07581978,0.32078072,-0.06063268,0.11560041,0.23668602,0.97285825,0.00011849090000000001
3,353.0,0.0,1008.0,1.0,1008.0,2885.0,0.4826735999999925,-20.0,-20.0,0.0,,,,,,,,,,,,,,,,-1.8720954986783211,0.7097144372888278,-0.3754689651451796,-3.3225778431943085,,,,,,,,,0.12676543,0.06586319,0.30209106,-0.04302346,0.06763674,0.17496337,0.88473463,9.743495999999999e-05
4,516.0,0.0,814.0,1.0,814.0,3699.0,0.474696399999989,-20.0,-20.0,0.0,,,,,,,,,,,,,,,,-2.193174392327956,0.69198455704147,-0.4780715307780122,-3.3372597252516765,,,,,,,,,0.10700438,0.038330942,0.31717354,0.03721839,0.10371645,0.23203200000000002,1.0052496,0.00057114265
5,703.0,0.0,932.0,1.0,932.0,4631.0,0.465562799999985,-21.0,-21.0,0.0,,,,,,,,,,,,,,,,-2.122317833023211,0.6454978854674346,-0.7105532272722921,-3.354852824180864,,,,,,,,,0.16040073,0.044896505999999996,0.29440245,0.063172355,0.04608961,0.11784693,0.5444492,0.00014167171000000002