1
0
mirror of https://github.com/gryf/coach.git synced 2026-02-13 04:15:45 +01:00
Files
coach/rl_coach/traces/Atari_DQN_pong/trace.csv
2018-08-20 13:01:30 +03:00

1.7 KiB

1Episode #Training IterIn HeatupER #TransitionsER #EpisodesEpisode LengthTotal stepsEpsilonShaped Training RewardTraining RewardUpdate Target NetworkEvaluation RewardShaped Evaluation RewardSuccess RateLoss/MeanLoss/StdevLoss/MaxLoss/MinLearning Rate/MeanLearning Rate/StdevLearning Rate/MaxLearning Rate/MinGrads (unclipped)/MeanGrads (unclipped)/StdevGrads (unclipped)/MaxGrads (unclipped)/MinQ/MeanQ/StdevQ/MaxQ/Min
210.01.01117.01117.01117.01117.01.00.0
32210.00.01958.01958.0841.01958.00.9992431000000248-20.0-20.00.00.0111585497797239520.012338007181564630.048920866101980217.747895870124921e-050.000100000000000000021.3552527156068802e-200.00010.00010.077657370.0514505020.272044099999999960.016480377
43402.00.02726.02726.0768.02726.00.9985519000000476-21.0-21.00.00.0116828784952266070.0139769866988062060.075509391725063323.554971408448182e-050.000100000000000000032.7105054312137605e-200.00010.00010.0549675670.037602150.236776470.0071376543000000010.0599240550.0100018219999999990.0705883650.045257278
54601.00.03519.03519.0793.03519.00.9978382000000712-21.0-21.00.00.0133313051950763870.0131628536027521940.04717267304658899.195879101753236e-050.00010.00.00010.00010.053911580.026416140.146995430.0179585680.0389104000000000050.0061192230000000010.0460090379999999950.030036567000000004
65837.00.04466.04466.0947.04466.00.9969859000000992-20.0-20.00.00.0112046461046270850.0128691550711813510.060537010431289676.284505798248574e-050.000100000000000000021.3552527156068802e-200.00010.00010.0471312480.0269142479999999980.132756960.010900318999999999