1
0
mirror of https://github.com/gryf/coach.git synced 2026-01-07 14:24:16 +01:00
Files
coach/rl_coach/traces/Atari_A3C_LSTM_pong/trace.csv
2018-10-02 17:55:16 +03:00

2.5 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)/MinDiscounted Return/MeanDiscounted Return/StdevDiscounted Return/MaxDiscounted Return/MinEntropy/MeanEntropy/StdevEntropy/MaxEntropy/MinAdvantages/MeanAdvantages/StdevAdvantages/MaxAdvantages/MinValues/MeanValues/StdevValues/MaxValues/MinValue Loss/MeanValue Loss/StdevValue Loss/MaxValue Loss/MinPolicy Loss/MeanPolicy Loss/StdevPolicy Loss/MaxPolicy Loss/Min
210.01.0772.01.0772.0772.00.00.0-2.4373320092098320.5666975756966289-0.7105532272722921-3.364332223379411
320.01.0821.01.0821.01593.00.00.0-2.33754274528531840.562882024173797-0.7105532272722921-3.3225778431943085
4338.00.0763.01.0763.02356.00.0-21.0-21.00.00.97898349999999991.3354245.441890.0016743626999999998-2.51780462024516940.5843148195084643-0.7105532272722921-3.36999824407674531.76760289999999980.035729731.7917061.671823-0.151976621779000480.424573580402482050.7191236019134521-1.0115903615951538-1.0943081.20643750.07422362-3.95627360000000030.185598020.180263180.56198880000000016.661260000000001e-06-0.275773580.581094260.6487745-1.4974867
5475.00.0740.01.0740.03096.00.0-21.0-21.00.02.04741741.19401550000000015.40717399999999950.46045935-2.5331846416598960.5861942513660167-0.7105532272722921-3.36999824407674531.41435680000000020.196159471.77795770000000021.165880.225331104795138040.45910706013657481.1359987258911133-0.9571647644042968-5.570110.6552074999999999-4.209009-6.24004130.27813680.125226990.574097450.159916310.318051040.51106179999999991.0385043999999999-0.8121315
65113.00.0755.01.0755.03851.00.0-21.0-21.00.01.57485039999999990.68864242.88869500000000020.46616986-2.52464311296112860.5835765895797549-0.7105532272722921-3.36999824407674531.21005060000000020.0291877311.49432581.14793530.083193990346547730.44093533728952121.0099096298217771-0.9640896320343018-4.0399050.5391477-3.5903852-5.54381230.1137604860.0475932620000000040.215749550.0624693930.09465530.44383180.6956541-0.781316