1
0
mirror of https://github.com/gryf/coach.git synced 2026-02-01 13:25:45 +01:00
Files
coach/rl_coach/traces/Atari_C51_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
32210.00.01958.01958.0841.01958.00.999167410000018-20.0-20.00.03.93024848756335960.0009802462733218353.93154168128967333.9268913269042970.00025000000000000011.0842021724855042e-190.000250.000250.00217406680.00232277799999999970.0147396340.0009191924499999999
43402.00.02726.02726.0768.02726.00.9984070900000346-21.0-21.00.03.9288378506898880.00105470643173554323.93019104003906343.92407798767089750.00025000000000000015.421010862427521e-200.000250.000250.00158340950000000020.00250856230000000030.0164218150.00053923610.063827644847334040.023589388739032840.100024540349841720.024584384262562403
54601.00.03519.03519.0793.03519.00.9976220200000516-21.0-21.00.03.9279921078801760.00100904220558908823.9291789531707763.9253447055816650.00025000000000000015.421010862427521e-200.000250.000250.00158886580.0028717520.0172853190.000373173970000000050.069213762817284040.0074289212152396650.081693614274264010.05617701336741498
65809.00.04352.04352.0833.04352.00.9967973500000696-21.0-21.00.03.9280170649290090.00094301714183156233.92898178100585943.923881292343140.00025000000000000011.0842021724855042e-190.000250.000250.00163489810.00317598620.0169660710.00030335260.072164758356909540.004362859879258740.076762536540627950.06509595513343866