gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2026-02-20 08:45:55 +01:00
Code Issues Projects Releases Wiki Activity
Files
72a1d9d426004269997f8b40bdd64f8ee582d91e
coach/rl_coach/traces/Atari_QR_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

6.2 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
6551.00.01260.01260.0203.01260.00.99979903000000445.055.00.036.4026457974139449.44809691530482198.95175170898440.19896247982978825.000000000000001e-056.776263578034403e-215e-055e-057.80670639999999957.39111759999999936.1821251.4651048
7670.00.01335.01335.075.01335.00.9997247800000062.015.00.039.2358043366356941.01677103106478599.570487976074220.2613675296306615e-050.05e-055e-0510.853987.77096270000000126.8008159999999982.6992220000000002
8791.00.01422.01422.087.01422.00.99963865000000781.015.00.038.020703694650147.816324507097775148.43403625488280.32468551397323615e-056.776263578034403e-215e-055e-0511.6300278.39127240.4025229999999954.429657499999999
98159.00.01693.01693.0271.01693.00.99937036000001365.055.00.028.94803325186914536.08735969022815148.068710327148440.36644464731216435.0000000000000016e-051.3552527156068802e-205e-055e-0511.1671199999999996.74828431.7834419999999974.7481833
109201.00.01861.01861.0168.01861.00.99920404000001723.050.00.018.98657363795098631.753488181878904146.003311157226560.36432319879531865.000000000000001e-056.776263578034403e-215e-055e-059.7016119999999997.38170543.526984.8068805
1110279.00.02172.02172.0311.02172.00.9988961500000244.065.00.032.0384772809652241.925721917185676194.551284790039030.29548773169517525.0000000000000016e-052.0328790734103208e-205e-055e-0518.14001799999999813.33114786.435683.4344087
1211440.00.02815.02815.0643.02815.00.998259580000037810.0335.00.028.06927355883284434.57541787899187143.409286499023440.48902463912963865.000000000000001e-056.776263578034403e-215e-055e-0521.0292914.073232105.4717257.1603360.0161829399437798840.003178820256121320.0206303630332695320.012337473193183542
1312458.00.02888.02888.073.02888.00.99818731000003942.045.00.030.9084128340085336.51044361360722138.053939819335941.17505180835723885e-050.05e-055e-0534.07071718.22935187.2968117.943182
1413478.00.02969.02969.081.02969.00.99810712000004120.00.00.021.81907897591590426.66760641513912694.146697998046881.24814236164093025e-050.05e-055e-0529.0881867.606013348.7212818.9277269999999970.0172325150918428980.0048422245077378580.0230452464552945470.011178828286356295
1514532.00.03183.03183.0214.03183.00.99789526000004564.050.00.022.00388450755013631.0137991846309393.176788330078120.77775686979293825.0000000000000016e-051.3552527156068802e-205e-055e-0525.91773599999999817.05690199999999782.9476849999999911.922298
1615551.00.03262.03262.079.03262.00.99781705000004742.015.00.026.50198901954450338.53608557260633132.78381347656250.77581745386123665e-050.05e-055e-0531.65451829.090153000000004115.0522199999999912.105766000000001
1716632.00.03584.03584.0322.03584.00.99749827000005446.0145.00.026.85574735999107431.176486537250174123.038970947265620.9733167290687565.000000000000001e-056.776263578034403e-215e-055e-0536.81529600000000422.30738154.8107814.8581970.0151874241049396630.0059427337564637850.022935437835112680.008310022529549316
1817671.00.03742.03742.0158.03742.00.99734185000005762.015.00.028.49203642362203232.6352845423457593.967338562011720.96520704030990594.999999999999999e-051.3552527156068802e-205e-055e-0534.65346500000000419.93393392.07970414.5869369999999990.0314954626786129660.0085527238109864050.048829601789184390.021028505007270725
1918692.00.03823.03823.081.03823.00.99726166000005942.015.00.025.05214429497719330.43845731410265125.729721069335941.78889465332031255e-050.05e-055e-0542.0916222.177326135.0619726.311890000000002
2019724.00.03954.03954.0131.03954.00.99713197000006243.060.00.022.73349286988377625.4878385890017185.92177581787111.16119325160980225e-050.05e-055e-0536.70792417.86990797.1635060000000117.332857
2120892.00.04624.04624.0670.04624.00.996468670000076810.0120.00.026.8219878587894132.463568352909114173.32832336425780.62746739387512215e-056.776263578034403e-215e-055e-0540.4393625.755894179.222959.7564770.031797291318301490.0159359859613298730.060863155482948070.005561185698170447
22211039.00.05212.05212.0588.05212.00.99588655000008927.0305.00.025.64262788595796730.19485814602498128.4826660156250.8743785023689275.0000000000000016e-051.3552527156068802e-205e-055e-0538.30828520.612198146.4784212.96736050.018670957953751590.004869771812786840.0255397156529215860.011338672893034526
23221062.00.05306.05306.094.05306.00.99579349000009121.030.00.027.77396630463392735.56498822181043128.786773681640620.77816641330718994.999999999999999e-051.3552527156068802e-205e-055e-0537.37607632.84612134.2358899999999810.897138
24231121.00.05540.05540.0234.05540.00.99556183000009635.065.00.027.4822864121404131.674095369737838117.51298522949221.53401458263397225.000000000000001e-056.776263578034403e-215e-055e-0547.45872530.501372999999997172.1448723.663988
25241159.00.05692.05692.0152.05692.00.99541135000009960.00.00.022.54871502989217229.715242718167897135.168853759765621.1777471303939824.999999999999999e-051.3552527156068802e-205e-055e-0537.8598622.92256141.6285118.90979
26251211.00.05901.05901.0209.05901.00.9952044400001043.055.00.020.99386624074899625.48031472078601295.076377868652340.89262783527374275.0000000000000016e-051.3552527156068802e-205e-055e-0528.6650714.32796700000000180.87813.025402
Reference in New Issue View Git Blame Copy Permalink