1
0
mirror of https://github.com/gryf/coach.git synced 2026-02-15 05:25:55 +01:00
Files
coach/rl_coach/traces/Atari_Bootstrapped_DQN_pong/trace.csv
itaicaspi-intel fa4895f840 new traces
2018-09-13 11:47:36 +03:00

1.9 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/MinQ/MeanQ/StdevQ/MaxQ/Min
210.01.0986.0986.0986.0986.07.00.0-1.82055450768214190.7192845707051421-0.2081522550905921-3.1698994392478896
320.01.01806.01806.0820.01806.04.00.0-2.33709693943518640.575288014748253-0.7105532272722921-3.355172823288848
43206.00.02629.02629.0823.02629.05.0-21.0-21.00.00.0132416460227370440.0134261157990749720.066926799714565280.0007059557829052210.00025000000000000011.0842021724855042e-190.000250.000250.0129832789999999990.0048818260.0328561630.00533005-2.33427228363145020.7834970909114538-0.38878391807422696-3.369599601005491
54398.00.03397.03397.0768.03397.03.0-21.0-21.00.00.0140171466437095660.0135810667699596660.063068725168704990.00067650509299710390.00025000000000000015.421010862427521e-200.000250.000250.0126320450.0043351360.025226240.005467761-2.44951404116649260.5558315778011723-0.7105532272722921-3.354852824180864
65617.00.04274.04274.0877.04274.06.0-21.0-21.00.00.0147816892548519530.0145629118179354880.078518502414226520.00112006091512739660.00025000000000000011.0842021724855042e-190.000250.000250.0127275739999999980.0045146210.0352981870.0072377953000000005-2.243862779517450.7822289069788971-0.3810471181045498-3.3685376079191567-0.0179595760.0162070130.0050252294-0.04572457