1
0
mirror of https://github.com/gryf/coach.git synced 2026-02-17 06:35:47 +01:00
Files
coach/rl_coach/traces/Mujoco_ClippedPPO_hopper/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

32 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)/MinEntropy/MeanEntropy/StdevEntropy/MaxEntropy/MinAdvantages/MeanAdvantages/StdevAdvantages/MaxAdvantages/MinValues/MeanValues/StdevValues/MaxValues/MinValue Loss/MeanValue Loss/StdevValue Loss/MaxValue Loss/MinPolicy Loss/MeanPolicy Loss/StdevPolicy Loss/MaxPolicy Loss/MinValue Targets/MeanValue Targets/StdevValue Targets/MaxValue Targets/MinKL Divergence/MeanKL Divergence/StdevKL Divergence/MaxKL Divergence/MinLikelihood Ratio/MeanLikelihood Ratio/StdevLikelihood Ratio/MaxLikelihood Ratio/MinClipped Likelihood Ratio/MeanClipped Likelihood Ratio/StdevClipped Likelihood Ratio/MaxClipped Likelihood Ratio/Min
210.01.017.01.017.017.00.100000000000000020.0
320.01.040.02.023.040.00.100000000000000020.0
430.01.055.03.015.055.00.100000000000000020.0
540.01.072.04.017.072.00.100000000000000020.0
650.01.081.05.09.081.00.100000000000000020.0
760.01.0102.06.021.0102.00.100000000000000020.0
870.01.0124.07.022.0124.00.100000000000000020.0
980.01.0138.08.014.0138.00.100000000000000020.0
1090.01.0157.09.019.0157.00.100000000000000020.0
11100.01.0188.010.031.0188.00.100000000000000020.0
12110.01.0201.011.013.0201.00.100000000000000020.0
13120.01.0212.012.011.0212.00.100000000000000020.0
14130.01.0245.013.033.0245.00.100000000000000020.0
15140.01.0255.014.010.0255.00.100000000000000020.0
16150.01.0280.015.025.0280.00.100000000000000020.0
17160.01.0306.016.026.0306.00.100000000000000020.0
18170.01.0317.017.011.0317.00.100000000000000020.0
19180.01.0341.018.024.0341.00.100000000000000020.0
20190.01.0352.019.011.0352.00.100000000000000020.0
21200.01.0376.020.024.0376.00.100000000000000020.0
22210.01.0391.021.015.0391.00.100000000000000020.0
23220.01.0432.022.041.0432.00.100000000000000020.0
24230.01.0455.023.023.0455.00.100000000000000020.0
25240.01.0479.024.024.0479.00.100000000000000020.0
26250.01.0529.025.050.0529.00.100000000000000020.0
27260.01.0545.026.016.0545.00.100000000000000020.0
28270.01.0563.027.018.0563.00.100000000000000020.0
29280.01.0584.028.021.0584.00.100000000000000020.0
30290.01.0603.029.019.0603.00.100000000000000020.0
31300.01.0626.030.023.0626.00.100000000000000020.0
32310.01.0648.031.022.0648.00.100000000000000020.0
33320.01.0661.032.013.0661.00.100000000000000020.0
34330.01.0675.033.014.0675.00.100000000000000020.0
35340.01.0695.034.020.0695.00.100000000000000020.0
36350.01.0703.035.08.0703.00.100000000000000020.0
37360.01.0721.036.018.0721.00.100000000000000020.0
38370.01.0735.037.014.0735.00.100000000000000020.0
39380.01.0746.038.011.0746.00.100000000000000020.0
40390.01.0794.039.048.0794.00.100000000000000020.0
41400.01.0816.040.022.0816.00.100000000000000020.0
42410.01.0837.041.021.0837.00.100000000000000020.0
43420.01.0853.042.016.0853.00.100000000000000020.0
44430.01.0869.043.016.0869.00.100000000000000020.0
45440.01.0885.044.016.0885.00.100000000000000020.0
46450.01.0914.045.029.0914.00.100000000000000020.0
47460.01.0945.046.031.0945.00.100000000000000020.0
48470.01.0958.047.013.0958.00.100000000000000020.0
49480.01.0988.048.030.0988.00.100000000000000020.0
50490.01.01004.049.016.01004.00.100000000000000020.0
51500.01.01032.050.028.01032.00.100000000000000020.0
52510.00.01044.051.012.01044.00.1000000000000000210.80581792008626410.8058179200862640.0
53520.00.01053.052.09.01053.00.100000000000000025.6656750437331435.6656750437331430.0
54530.00.01072.053.019.01072.00.100000000000000028.8305563035084118.8305563035084110.0
55540.00.01087.054.015.01087.00.1000000000000000211.6641161088827211.664116108882720.0
56550.00.01098.055.011.01098.00.100000000000000025.0291817789452785.0291817789452780.0
57560.00.01123.056.025.01123.00.1000000000000000223.00192695421150223.0019269542115020.0
58570.00.01142.057.019.01142.00.1000000000000000218.0708126025343218.070812602534320.0
59580.00.01162.058.020.01162.00.1000000000000000216.79809146935759816.7980914693575980.0
60590.00.01182.059.020.01182.00.1000000000000000213.31810238327465613.3181023832746560.0
61600.00.01195.060.013.01195.00.1000000000000000211.15579908353766411.1557990835376640.0
62610.00.01203.061.08.01203.00.100000000000000025.7724302238237375.7724302238237370.0
63620.00.01217.062.014.01217.00.1000000000000000213.02638404509674313.0263840450967430.0
64630.00.01252.063.035.01252.00.1000000000000000223.1123197990768723.112319799076870.0
65640.00.01296.064.044.01296.00.1000000000000000242.937544977732942.93754497773290.0
66650.00.01305.065.09.01305.00.100000000000000025.4060194337615875.4060194337615870.0
67660.00.01312.066.07.01312.00.100000000000000024.7880904945883584.7880904945883580.0
68670.00.01327.067.015.01327.00.1000000000000000210.81559378086063610.8155937808606360.0
69680.00.01339.068.012.01339.00.100000000000000029.148786310560129.148786310560120.0
70690.00.01354.069.015.01354.00.1000000000000000211.34323159695528811.3432315969552880.0
71700.00.01379.070.025.01379.00.1000000000000000225.4039301280925625.403930128092560.0
72710.00.01394.071.015.01394.00.100000000000000026.6124234270998516.6124234270998510.0
73720.00.01402.072.08.01402.00.100000000000000025.7335174610265715.7335174610265710.0
74730.00.01416.073.014.01416.00.1000000000000000213.91256977482205313.9125697748220530.0
75740.00.01436.074.020.01436.00.1000000000000000217.31609118002359817.3160911800235980.0
76750.00.01446.075.010.01446.00.100000000000000026.54705871355351656.54705871355351650.0
77760.00.01474.076.028.01474.00.1000000000000000226.4751785652378926.475178565237890.0
78770.00.01483.077.09.01483.00.100000000000000027.1539932847574177.1539932847574170.0
79780.00.01494.078.011.01494.00.100000000000000029.124111729401419.124111729401410.0
80790.00.01516.079.022.01516.00.100000000000000029.4736677677559049.4736677677559040.0
81800.00.01527.080.011.01527.00.100000000000000028.5773305520862638.5773305520862630.0
82810.00.01555.081.028.01555.00.1000000000000000227.927412254870427.92741225487040.0
83820.00.01582.082.027.01582.00.1000000000000000222.00586491887881422.0058649188788140.0
84830.00.01597.083.015.01597.00.1000000000000000211.37594084590619511.3759408459061950.0
85840.00.01637.084.040.01637.00.1000000000000000253.4086122900259253.408612290025920.0
86850.00.01647.085.010.01647.00.100000000000000027.269760872545017.269760872545010.0
87860.00.01664.086.017.01664.00.1000000000000000210.72115767771559510.7211576777155950.0
88870.00.01675.087.011.01675.00.100000000000000027.9342659651075037.9342659651075030.0
89880.00.01705.088.030.01705.00.1000000000000000219.08677804183531619.0867780418353160.0
90890.00.01724.089.019.01724.00.1000000000000000215.39319617921329815.3931961792132980.0
91900.00.01742.090.018.01742.00.1000000000000000210.51318705099027510.5131870509902750.0
92910.00.01773.091.031.01773.00.1000000000000000216.14623316217356616.1462331621735660.0
93920.00.01789.092.016.01789.00.1000000000000000213.81247541402748313.8124754140274830.0
94930.00.01798.093.09.01798.00.100000000000000026.791510881357286.791510881357280.0
95940.00.01810.094.012.01810.00.1000000000000000210.6218913616193910.621891361619390.0
96950.00.01826.095.016.01826.00.100000000000000028.8640340051217758.8640340051217750.0
97960.00.01836.096.010.01836.00.100000000000000026.6976036600948316.6976036600948310.0
98970.00.01846.097.010.01846.00.100000000000000027.1605139259690767.1605139259690760.0
99980.00.01856.098.010.01856.00.100000000000000028.3120893513482548.3120893513482540.0
100990.00.01884.099.028.01884.00.1000000000000000211.05649755023173411.0564975502317340.0
1011000.00.01916.0100.032.01916.00.1000000000000000236.6617624544103436.661762454410340.0
1021010.00.01939.0101.023.01939.00.1000000000000000213.24959056571580613.2495905657158060.0
1031020.00.01961.0102.022.01961.00.100000000000000027.0616263757679557.0616263757679550.0
1041030.00.01974.0103.013.01974.00.1000000000000000210.1848860935007210.184886093500720.0
1051040.00.01990.0104.016.01990.00.1000000000000000210.51142458145794510.5114245814579450.0
1061050.00.01998.0105.08.01998.00.100000000000000025.15662740029955655.15662740029955650.0
1071060.00.02006.0106.08.02006.00.100000000000000025.01479745655049855.01479745655049850.0
1081070.00.02019.0107.013.02019.00.1000000000000000211.16248724137784411.1624872413778440.0
1091080.00.02026.0108.07.02026.00.100000000000000025.5062324610956295.5062324610956290.0
1101090.00.02044.0109.018.02044.00.1000000000000000212.81813496958328712.8181349695832870.0
1111100.00.02055.0110.011.02055.00.100000000000000028.9048968572257888.9048968572257880.0
1121111.00.024.01.024.02079.00.1000000000000000232.3999981500264832.399998150026480.0
1131121.00.045.02.021.02100.00.100000000000000029.3502631619281199.3502631619281190.0
1141131.00.060.03.015.02115.00.100000000000000026.3410779689182066.3410779689182060.0
1151141.00.0105.04.045.02160.00.1000000000000000245.1658137887998445.165813788799840.0
1161151.00.0121.05.016.02176.00.1000000000000000215.41888216433510615.4188821643351060.0
1171161.00.0134.06.013.02189.00.100000000000000029.4797712113933499.4797712113933490.0
1181171.00.0149.07.015.02204.00.100000000000000027.1489929408818227.1489929408818220.0
1191181.00.0182.08.033.02237.00.1000000000000000236.07892627798679536.0789262779867950.0
1201191.00.0191.09.09.02246.00.100000000000000027.3890840521251567.3890840521251560.0
1211201.00.0205.010.014.02260.00.100000000000000028.5126935846048438.5126935846048430.0
1221211.00.0242.011.037.02297.00.1000000000000000221.14612134386516521.1461213438651650.0
1231221.00.0261.012.019.02316.00.1000000000000000211.80470654743076211.8047065474307620.0
1241231.00.0271.013.010.02326.00.100000000000000027.1224666699874387.1224666699874380.0
1251241.00.0286.014.015.02341.00.100000000000000029.3435202022804119.3435202022804110.0
1261251.00.0295.015.09.02350.00.100000000000000026.8218692645634196.8218692645634190.0
1271261.00.0335.016.040.02390.00.1000000000000000242.8591827827645342.859182782764530.0
1281271.00.0359.017.024.02414.00.1000000000000000228.35129661763744528.3512966176374450.0
1291281.00.0370.018.011.02425.00.1000000000000000210.40183886711457210.4018388671145720.0
1301291.00.0394.019.024.02449.00.1000000000000000219.288246331435219.28824633143520.0
1311301.00.0426.020.032.02481.00.1000000000000000241.45976334818363541.4597633481836350.0
1321311.00.0474.021.048.02529.00.1000000000000000238.98497886273557438.9849788627355740.0
1331321.00.0489.022.015.02544.00.1000000000000000214.36458567527345514.3645856752734550.0
1341331.00.0515.023.026.02570.00.1000000000000000216.9133832075680316.913383207568030.0
1351341.00.0526.024.011.02581.00.100000000000000026.4369726218767956.4369726218767950.0
1361351.00.0544.025.018.02599.00.100000000000000029.215163036688169.215163036688160.0
1371361.00.0564.026.020.02619.00.1000000000000000220.13904740113324720.1390474011332470.0
1381371.00.0584.027.020.02639.00.1000000000000000221.24574170539184721.2457417053918470.0
1391381.00.0621.028.037.02676.00.1000000000000000222.3253781461720322.325378146172030.0
1401391.00.0655.029.034.02710.00.1000000000000000254.2134601472870254.213460147287020.0
1411401.00.0669.030.014.02724.00.1000000000000000210.87729310762230210.8772931076223020.0
1421411.00.0690.031.021.02745.00.1000000000000000216.76655220619763416.7665522061976340.0
1431421.00.0703.032.013.02758.00.1000000000000000212.69484905863223812.6948490586322380.0
1441431.00.0727.033.024.02782.00.1000000000000000227.96078645035633427.9607864503563340.0
1451441.00.0749.034.022.02804.00.1000000000000000217.42996280078641317.4299628007864130.0
1461451.00.0781.035.032.02836.00.1000000000000000238.60225565969397438.6022556596939740.0
1471461.00.0802.036.021.02857.00.1000000000000000218.5335048252305618.533504825230560.0
1481471.00.0816.037.014.02871.00.1000000000000000212.80389049256776912.8038904925677690.0
1491481.00.0866.038.050.02921.00.1000000000000000239.79679129634157439.7967912963415740.0
1501491.00.0880.039.014.02935.00.1000000000000000214.84995747901424314.8499574790142430.0
1511501.00.0919.040.039.02974.00.1000000000000000254.3010345259180954.301034525918090.0
1521511.00.0947.041.028.03002.00.1000000000000000223.21663191967815723.2166319196781570.0
1531521.00.0963.042.016.03018.00.1000000000000000213.17666632565317813.1766663256531780.0
1541531.00.01006.043.043.03061.00.1000000000000000233.61954423361538633.6195442336153860.0
1551541.00.01056.044.050.03111.00.1000000000000000272.1425183735944772.142518373594470.0
1561551.00.01071.045.015.03126.00.100000000000000028.4737729643802798.4737729643802790.0
1571561.00.01102.046.031.03157.00.100000000000000024.7825546361925054.7825546361925050.0
1581571.00.01124.047.022.03179.00.1000000000000000223.8079464032818723.807946403281870.0
1591581.00.01182.048.058.03237.00.1000000000000000243.6707621179874343.670762117987430.0
1601591.00.01200.049.018.03255.00.1000000000000000216.19342042260243616.1934204226024360.0
1611601.00.01219.050.019.03274.00.1000000000000000220.80443301968271220.8044330196827120.0
1621611.00.01238.051.019.03293.00.1000000000000000213.73450948019489313.7345094801948930.0
1631621.00.01263.052.025.03318.00.1000000000000000211.92332705111074611.9233270511107460.0
1641631.00.01301.053.038.03356.00.1000000000000000217.44537825609656417.4453782560965640.0
1651641.00.01315.054.014.03370.00.1000000000000000214.12680976333258614.1268097633325860.0
1661651.00.01352.055.037.03407.00.1000000000000000251.66809107462075451.6680910746207540.0
1671661.00.01367.056.015.03422.00.1000000000000000211.01454064223232411.0145406422323240.0
1681671.00.01420.057.053.03475.00.1000000000000000225.2031249780033525.203124978003350.0
1691681.00.01434.058.014.03489.00.1000000000000000213.72617750089597513.7261775008959750.0
1701691.00.01483.059.049.03538.00.1000000000000000245.4156100449470345.415610044947030.0
1711701.00.01500.060.017.03555.00.1000000000000000212.18459494193618512.1845949419361850.0
1721711.00.01537.061.037.03592.00.1000000000000000215.40652530153751215.4065253015375120.0
1731721.00.01552.062.015.03607.00.1000000000000000214.12538982922346514.1253898292234650.0
1741731.00.01567.063.015.03622.00.1000000000000000210.12837859572162810.1283785957216280.0
1751741.00.01600.064.033.03655.00.1000000000000000243.5095322427728943.509532242772890.0
1761751.00.01619.065.019.03674.00.1000000000000000220.19337984115907520.1933798411590750.0
1771761.00.01628.066.09.03683.00.100000000000000025.8432616957671775.8432616957671770.0
1781771.00.01639.067.011.03694.00.100000000000000029.2085197694745659.2085197694745650.0
1791781.00.01683.068.044.03738.00.1000000000000000246.18680628947450446.1868062894745040.0
1801791.00.01704.069.021.03759.00.1000000000000000212.72977941119701712.7297794111970170.0
1811801.00.01721.070.017.03776.00.1000000000000000217.4599961547576517.459996154757650.0
1821811.00.01753.071.032.03808.00.1000000000000000233.46064108548867533.4606410854886750.0
1831821.00.01765.072.012.03820.00.100000000000000029.1351278813073349.1351278813073340.0
1841831.00.01787.073.022.03842.00.1000000000000000223.50285730836936823.5028573083693680.0
1851841.00.01816.074.029.03871.00.100000000000000027.6328407668317817.6328407668317810.0
1861851.00.01921.075.0105.03976.00.10000000000000002189.99723881996326189.997238819963260.0
1871861.00.01938.076.017.03993.00.1000000000000000214.96325678107131614.9632567810713160.0
1881871.00.01954.077.016.04009.00.1000000000000000210.4703681433189210.470368143318920.0
1891881.00.01977.078.023.04032.00.1000000000000000225.0508274139048225.050827413904820.0
1901891.00.02000.079.023.04055.00.1000000000000000214.29654815377369614.2965481537736960.0
1911901.00.02040.080.040.04095.00.1000000000000000259.60244581369382659.6024458136938260.0
1921911.00.02051.081.011.04106.00.100000000000000028.451454414343818.451454414343810.0
1931922.00.034.01.034.04140.00.1000000000000000242.62500154084981642.6250015408498160.0
1941932.00.088.02.054.04194.00.1000000000000000256.1747588646042256.174758864604220.0
1951942.00.0123.03.035.04229.00.1000000000000000243.47156309388484643.4715630938848460.0
1961952.00.0206.04.083.04312.00.10000000000000002104.38884566686559104.388845666865590.0
1971962.00.0229.05.023.04335.00.1000000000000000216.4384787233313416.438478723331340.0
1981972.00.0270.06.041.04376.00.1000000000000000229.11808482791455429.1180848279145540.0
1991982.00.0328.07.058.04434.00.1000000000000000288.9721009080556788.972100908055670.0
2001992.00.0409.08.081.04515.00.10000000000000002144.18442372071513144.184423720715130.0
2012002.00.0479.09.070.04585.00.1000000000000000273.7486021837420273.748602183742020.0
2022012.00.0560.010.081.04666.00.10000000000000002110.5873293901508110.58732939015080.0
2032022.00.0622.011.062.04728.00.1000000000000000271.5889681052166871.588968105216680.0
2042032.00.0747.012.0125.04853.00.10000000000000002169.85339841901748169.853398419017480.0
2052042.00.0805.013.058.04911.00.1000000000000000241.4528757741435941.452875774143590.0
2062052.00.0839.014.034.04945.00.1000000000000000239.6171883577068639.617188357706860.0
2072062.00.0947.015.0108.05053.00.10000000000000002218.5020645486265218.50206454862650.0
2082072.00.0983.016.036.05089.00.1000000000000000242.41293878889245442.4129387888924540.0
2092082.00.01029.017.046.05135.00.1000000000000000257.115125366645257.11512536664520.0
2102092.00.01049.018.020.05155.00.1000000000000000217.23942872637823217.2394287263782320.0
2112102.00.01068.019.019.05174.00.1000000000000000210.379776462718210.37977646271820.0
2122112.00.01124.020.056.05230.00.1000000000000000296.8120827374365496.812082737436540.0
2132122.00.01153.021.029.05259.00.1000000000000000234.6803175038294634.680317503829460.0
2142132.00.01178.022.025.05284.00.1000000000000000222.52526065813132722.5252606581313270.0
2152142.00.01202.023.024.05308.00.1000000000000000226.8332899199656426.833289919965640.0
2162152.00.01270.024.068.05376.00.10000000000000002103.96404077308901103.964040773089010.0
2172162.00.01331.025.061.05437.00.1000000000000000284.2706073724843684.270607372484360.0
2182172.00.01381.026.050.05487.00.1000000000000000263.2810931851830763.281093185183070.0
2192182.00.01394.027.013.05500.00.1000000000000000211.35791283036192611.3579128303619260.0
2202192.00.01415.028.021.05521.00.1000000000000000223.84333716936285823.8433371693628580.0
2212202.00.01469.029.054.05575.00.1000000000000000277.834974716968777.83497471696870.0
2222212.00.01577.030.0108.05683.00.10000000000000002193.14414742576193.144147425760.0
2232222.00.01647.031.070.05753.00.10000000000000002108.3755200909245108.37552009092450.0
2242232.00.01672.032.025.05778.00.1000000000000000224.27593863085390424.2759386308539040.0
2252242.00.01721.033.049.05827.00.1000000000000000280.8436973898195180.843697389819510.0
2262252.00.01758.034.037.05864.00.1000000000000000234.5281893006165734.528189300616570.0