1
0
mirror of https://github.com/gryf/coach.git synced 2026-02-15 13:35:55 +01:00
Files
coach/rl_coach/traces/Atari_QR_DQN_pong/trace.csv
2018-08-20 13:01:30 +03:00

1.8 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
32210.00.01958.01958.0841.01958.00.999167410000018-20.0-20.00.037.3049736386253740.199281603456505153.43025207519532.4678487777709965.000000000000001e-056.776263578034403e-215e-055e-0514.60350100000000110.57843780.693343.9762766000000003
43402.00.02726.02726.0768.02726.00.9984070900000346-21.0-21.00.038.0794725529849543.23459368266095241.535156252.3205261230468755.0000000000000016e-051.3552527156068802e-205e-055e-0532.86752723.103817000000003127.041069999999998.249042-0.017844910274992190.007088911611692895-0.009264047715696506-0.027098445154260846
54601.00.03519.03519.0793.03519.00.9976220200000516-21.0-21.00.040.7898558468075836.92834222767065138.938781738281222.96691894531255e-050.05e-055e-0562.5944199999999933.358902183.728626.568246999999996-0.0393464347555224360.004771626651866583-0.03437434455496259-0.04845772998523898
65809.00.04352.04352.0833.04352.00.9967973500000696-21.0-21.00.034.6984570920467435.17935046195014175.62956237792972.9694447517395025.0000000000000016e-051.3552527156068802e-205e-055e-0554.86523399999999428.737910999999997232.9414200000000226.412553999999997-0.035892458057278420.005320110982296958-0.028433983605063988-0.045204031605389904