gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2026-01-30 12:15:49 +01:00
Code Issues Projects Releases Wiki Activity
Files
72a1d9d426004269997f8b40bdd64f8ee582d91e
coach/rl_coach/traces/Atari_DQN_space_invaders/trace.csv
Itai Caspi 72a1d9d426 Itaicaspi/episode reset refactoring (#105) 
* reordering of the episode reset operation and allowing to store episodes only when they are terminated

* reordering of the episode reset operation and allowing to store episodes only when they are terminated

* revert tensorflow-gpu to 1.9.0 + bug fix in should_train()

* tests readme file and refactoring of policy optimization agent train function

* Update README.md

* Update README.md

* additional policy optimization train function simplifications

* Updated the traces after the reordering of the environment reset

* docker and jenkins files

* updated the traces to the ones from within the docker container

* updated traces and added control suite to the docker

* updated jenkins file with the intel proxy + updated doom basic a3c test params

* updated line breaks in jenkins file

* added a missing line break in jenkins file

* refining trace tests ignored presets + adding a configurable beta entropy value

* switch the order of trace and golden tests in jenkins + fix golden tests processes not killed issue

* updated benchmarks for dueling ddqn breakout and pong

* allowing dynamic updates to the loss weights + bug fix in episode.update_returns

* remove docker and jenkins file
2018-09-04 15:07:54 +03:00

5.0 KiB
Raw Blame History

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
210.01.0486.0486.0486.0486.01.00.0
320.01.0573.0573.087.0573.01.00.0
430.01.0722.0722.0149.0722.01.00.0
540.01.01057.01057.0335.01057.01.00.0
6551.00.01260.01260.0203.01260.00.9998173000000065.055.00.00.0111533678549070230.0150270353755153560.05898782610893258.134254312608391e-050.000100000000000000021.3552527156068802e-200.00010.00010.048834430.0413943120.194765630.006623836700000001
7670.00.01335.01335.075.01335.00.99974980000000822.015.00.00.011477036266832760.0113259701912397280.0303077511489391330.00048297073226422070.00010.00.00010.00010.0561458360.0268539150.106006560.024553476
8791.00.01422.01422.087.01422.00.99967150000001081.015.00.00.0115486591793818490.0137308098991240570.0432423353195190360.00030534103279933330.00011.3552527156068802e-200.00010.00010.0598777759999999940.036879020.137173060.020375967
98159.00.01693.01693.0271.01693.00.99942760000001885.055.00.00.0087163239344346340.0106179091789540290.04300096631050110.000197978850337676680.000100000000000000032.7105054312137605e-200.00010.00010.047586730.031713870.137692120.011469088999999998
109201.00.01861.01861.0168.01861.00.99927640000002383.050.00.00.0057721662302529210.0093137487137902940.042694322764873510.00012825922749470920.000100000000000000021.3552527156068802e-200.00010.00010.0346786570.0279402770000000030.12905760.008978493
1110279.00.02172.02172.0311.02172.00.99899650000003294.065.00.00.009666543763346570.0124556702215744410.057542331516742716.935953570064156e-050.000100000000000000034.0657581468206416e-200.00010.00010.0485039870.0370417570.15681950.006075088
1211406.00.02681.02681.0509.02681.00.9985384000000489.0320.00.00.0082861958460022490.0102380341438619220.0444227606058120660.000146337028127163650.00011.3552527156068802e-200.00010.00010.045928450.0305035080.141864550.01103545350.033225210.0159400870.0566093140.0076417234
1312471.00.02941.02941.0260.02941.00.99830440000005587.0110.00.00.0095455036507561230.0128119657452341550.057285502552986150.000149542436702176930.000100000000000000021.3552527156068802e-200.00010.00010.048353860.031749180.152124120.012202092
1413506.00.03082.03082.0141.03082.00.998177500000060.00.00.00.0079860915970389870.0102276534599123320.0291476212441921230.000184075906872749330.00011.3552527156068802e-200.00010.00010.0436419959999999950.031913850.114312640.012298575
1514569.00.03331.03331.0249.03331.00.99795340000006747.0110.00.00.0079284474688334270.0095491528184792860.042287811636924740.000134591507958248260.000100000000000000032.7105054312137605e-200.00010.00010.044255440.030100410.139628110.0104794
1615655.00.03677.03677.0346.03677.00.99764200000007760.00.00.00.0091161274584348660.0102333415209140180.038748282939195630.000160952593432739389.999999999999998e-052.7105054312137605e-200.00010.00010.050152960.0301245260000000020.134942840.0123188880.0369548460.0165411630.061376290.0047242693
1716674.00.03753.03753.076.03753.00.997573600000081.010.00.00.0054572594886657930.0067252423178196290.0154147557914257030.000189846192370168860.00010.00.00010.00010.0365321520000000050.0228976480.069118520.013080008999999998
1817723.00.03948.03948.0195.03948.00.99739810000008560.00.00.00.0063455837301503660.010182647699611620.03973073512315759.957021393347532e-050.000100000000000000021.3552527156068802e-200.00010.00010.038864880.0381842779999999950.141769190.006970413000000001
1918754.00.04073.04073.0125.04073.00.99728560000008942.015.00.00.0060267819255034650.0073502320077243980.0262754559516906740.000177694513695314539.999999999999996e-054.0657581468206416e-200.00010.00010.0433487330.0272569729999999970.125862760.011062483
2019831.00.04381.04381.0308.04381.00.99700840000009844.090.00.00.0065341613968107060.0090797225558639160.0397417917847633367.733125676168129e-050.000100000000000000032.7105054312137605e-200.00010.00010.0421011860.032505190.159256130.0062198965000000005
2120933.00.04789.04789.0408.04789.00.99664120000011065.035.00.00.0073086999398262440.0099060212632697320.054274391382932660.000116324830742087230.00011.3552527156068802e-200.00010.00010.042259550.0314866270.175790860.00773125370.0264195350.014258590.057565320.014857713
Reference in New Issue View Git Blame Copy Permalink