gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2026-01-26 01:15:45 +01:00
Code Issues Projects Releases Wiki Activity
Files
72a1d9d426004269997f8b40bdd64f8ee582d91e
coach/rl_coach/traces/CartPole_DFP/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

13 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)/Min
210.01.013.01.013.013.00.50.0
320.01.029.02.016.029.00.50.0
430.01.056.03.027.056.00.50.0
540.01.067.04.011.067.00.50.0
650.01.077.05.010.077.00.50.0
760.01.094.06.017.094.00.50.0
870.01.0106.07.012.0106.00.50.0
980.01.0121.08.015.0121.00.50.0
1090.01.0138.09.017.0138.00.50.0
11100.01.0172.010.034.0172.00.50.0
12110.01.0187.011.015.0187.00.50.0
13120.01.0201.012.014.0201.00.50.0
14130.01.0218.013.017.0218.00.50.0
15140.01.0235.014.017.0235.00.50.0
16150.01.0262.015.027.0262.00.50.0
17160.01.0279.016.017.0279.00.50.0
18170.01.0330.017.051.0330.00.50.0
19180.01.0350.018.020.0350.00.50.0
20190.01.0402.019.052.0402.00.50.0
21200.01.0411.020.09.0411.00.50.0
22210.01.0448.021.037.0448.00.50.0
23220.01.0462.022.014.0462.00.50.0
24230.01.0498.023.036.0498.00.50.0
25240.01.0510.024.012.0510.00.50.0
26250.01.0529.025.019.0529.00.50.0
27260.01.0554.026.025.0554.00.50.0
28270.01.0566.027.012.0566.00.50.0
29280.01.0618.028.052.0618.00.50.0
30290.01.0644.029.026.0644.00.50.0
31300.01.0660.030.016.0660.00.50.0
32310.01.0693.031.033.0693.00.50.0
33320.01.0707.032.014.0707.00.50.0
34330.01.0723.033.016.0723.00.50.0
35340.01.0736.034.013.0736.00.50.0
36350.01.0767.035.031.0767.00.50.0
37360.01.0778.036.011.0778.00.50.0
38370.01.0800.037.022.0800.00.50.0
39380.01.0825.038.025.0825.00.50.0
40390.01.0845.039.020.0845.00.50.0
41400.01.0867.040.022.0867.00.50.0
42410.01.0916.041.049.0916.00.50.0
43420.01.0930.042.014.0930.00.50.0
44430.01.0952.043.022.0952.00.50.0
45440.01.0964.044.012.0964.00.50.0
46450.01.0984.045.020.0984.00.50.0
47460.01.0994.046.010.0994.00.50.0
48470.01.01011.047.017.01011.00.50.0
49480.01.01043.048.032.01043.00.50.0
504911.00.01055.049.012.01055.00.498039999999999812.012.00.0407.0091802423650659.043146373400866474.9180908203125313.10388183593750.00010.00.00010.0001430.84777.9088535.00134292.06775
515030.00.01074.050.019.01074.00.494936666666666219.019.00.0361.8770395914714357.571153220720284461.5362243652344265.372589111328070.00010.00.00010.0001311.666995.65562527.886183.04402
525139.00.01083.051.09.01083.00.49346666666666619.09.00.0290.571222305297828.592770250767426324.0646667480469233.89793395996090.00010.00.00010.0001156.3647555.23453000000001266.0235380.92598000000001
535257.00.01101.052.018.01101.00.490526666666665818.018.00.0302.524062212775851.07200591011856397.303466796875215.76815795898440.00010.00.00010.0001125.0042649999999943.877303999999995221.1786200000000247.998363
545385.00.01129.053.028.01129.00.48595333333333228.028.00.0273.576790138527241.09384043429787369.19329833984375200.97407531738280.00011.3552527156068802e-200.00010.0001148.7957255.79693265.2249799999999653.90749
5554108.00.01152.054.023.01152.00.48219666666666523.023.00.0280.49879871715245.31952722484967382.5701599121094209.293350219726560.00011.3552527156068802e-200.00010.0001137.5391100000000255.1492243.3709164.81319
5655132.00.01176.055.024.01176.00.478276666666664624.024.00.0265.326893682065247.88051442596014345.6749267578125176.473251342773449.999999999999998e-052.7105054312137605e-200.00010.0001127.2849399999999943.462986228.5064799999999853.6738
5756171.00.01215.056.039.01215.00.47190666666666439.039.00.0259.5498576917146435.00860201428681329.51629638671875195.736709594726569.999999999999998e-052.7105054312137605e-200.00010.0001127.8356899999999955.49781361.577562.36788000000001
5857220.00.01264.057.049.01264.00.4639033333333349.049.00.0234.3201716740926539.67762681655549348.2401123046875148.272613525390620.00010.00.00010.0001130.7650100000000247.790714293.1360200000000378.02848
5958265.00.01309.058.045.01309.00.456553333333329345.045.00.0217.5844456065784728.633086540237922284.46954345703125156.800964355468750.000100000000000000032.7105054312137605e-200.00010.0001149.5161741.31043302.4673200000000393.088844
6059315.00.01359.059.050.01359.00.448386666666661850.050.00.0181.8311806503607228.659748770026674252.75552368164062124.990882873535160.000100000000000000021.3552527156068802e-200.00010.0001157.7390743.210159999999995277.414183.70544
6160381.00.01425.060.066.01425.00.437606666666660866.066.00.0162.6621938852163424.674537191314286233.25091552734372113.674896240234380.000100000000000000021.3552527156068802e-200.00010.0001148.7451642.076153000000005256.4686299999999668.96061
6261421.00.01465.061.040.01465.00.431073333333326940.040.00.0145.7967228033603519.751329689793014198.105453491210996.395591735839849.999999999999998e-052.7105054312137605e-200.00010.0001146.9576899999999965.732925313.1920851.533184000000006
6362456.00.01500.062.035.01500.00.425356666666659735.035.00.0131.1105568829704916.95306181555285186.766479492187599.964294433593760.00011.3552527156068802e-200.00010.0001132.6529553.839237304.4895662.909325
6463508.00.01552.063.052.01552.00.416863333333325652.052.00.0126.5335021673464415.481871151448455164.838546752929791.16052246093750.000100000000000000021.3552527156068802e-200.00010.0001152.1098588.43235385.3808339.948209999999996
6564562.00.01606.064.054.01606.00.408043333333324754.054.00.0118.9831491146447613.810711322823195152.5181579589843878.31948089599610.000100000000000000032.7105054312137605e-200.00010.0001138.2689267.992775326.9730242.56321
6665639.00.01683.065.077.01683.00.395466666666656977.077.00.0117.5855234045731414.767237376582813145.694458007812576.06152343750.000100000000000000032.7105054312137605e-200.00010.0001139.9309768.41799359.2681334.659209999999995
6766702.00.01746.066.063.01746.00.385176666666655963.063.00.0120.6752249194729712.975251902989402149.6554565429687586.923751831054690.000100000000000000032.7105054312137605e-200.00010.0001194.05127112.72679523.893745.209587
6867758.00.01802.067.056.01802.00.376029999999988456.056.00.0114.2924038973721511.037394276667747142.7156066894531284.414215087890620.000100000000000000034.0657581468206416e-200.00010.0001167.9101389.38369499.410445.970905
6968855.00.01899.068.097.01899.00.3601866666666535597.097.00.0108.8493096828460710.904272250219288136.3005828857422280.567390441894530.000100000000000000032.7105054312137605e-200.00010.0001166.0417585.99049000000001520.8202538.817432000000004
7069943.00.01987.069.088.01987.00.345813333333318988.088.00.0107.0251938392375911.39347761396693136.3988647460937878.002716064453129.999999999999998e-052.7105054312137605e-200.00010.0001210.01866110.30383567.111460.903659999999995
7170996.00.02040.070.053.02040.00.337156666666651453.053.00.0104.30463350736189.90557600777946122.7456207275390681.935752868652340.000100000000000000032.7105054312137605e-200.00010.0001224.59392999999997108.33842487.326768.59164399999999
72711066.00.02110.071.070.02110.00.32572333333331770.070.00.099.8402182537576612.33210844148148139.1262512207031278.96081542968750.000100000000000000032.7105054312137605e-200.00010.0001209.42502110.90117597.6600373.1405
73721153.00.02197.072.087.02197.00.311513333333315787.087.00.096.650155976761219.84319531790892123.9534530639648476.585029602050789.999999999999998e-052.7105054312137605e-200.00010.0001216.96257000000003121.00806399999999613.552259.14050699999999
74731276.00.02320.073.0123.02320.00.29142333333331377123.0123.00.097.3966297712482312.261304899663234137.8868255615234474.047058105468750.000100000000000000021.3552527156068802e-200.00010.0001230.93216129.7123612.310751.633354
75741376.00.02420.074.0100.02420.00.2750899999999789100.0100.00.0100.0224055280589312.402266865856195129.2123870849609476.035942077636720.00010.00.00010.0001333.58328215.783751084.733659.14518
76751474.00.02518.075.098.02518.00.2590833333333107498.098.00.0100.2463735206839911.541501085409068135.8545989990234479.600646972656250.000100000000000000021.3552527156068802e-200.00010.0001291.26004180.40565992.347655.43
77761630.00.02674.076.0156.02674.00.23360333333331115156.0156.00.096.714529665054812.927063203207426135.0385437011718869.762649536132810.00010.00.00010.0001318.5015187.476441042.650855.259426
78771790.00.02834.077.0160.02834.00.2074699999999798160.0160.00.097.2860817099517314.586646821280398148.7171325683593863.416435241699229.999999999999998e-052.7105054312137605e-200.00010.0001428.08205999999996299.959531505.861953.030354
79781985.00.03029.078.0195.03029.00.17561999999998226195.0195.00.094.2365486302326611.872838615596594124.6362686157226664.612075805664060.000100000000000000021.3552527156068802e-200.00010.0001388.60703246.096041546.416470.24545
80792064.00.03108.079.079.03108.00.1627166666666498879.079.00.095.2098708519568812.796128483766026124.2572479248046966.863998413085940.000100000000000000034.0657581468206416e-200.00010.0001441.08117999999996244.47371173.630591.54683
81802261.00.03305.080.0197.03305.00.13053999999998567197.0197.00.091.8196437796767814.275220726968213153.109664916992260.525394439697270.000100000000000000021.3552527156068802e-200.00010.0001438.85402999999997290.96261554.454672.2978
82812459.00.03503.081.0198.03503.00.09819999999998584198.0198.00.087.4364694120920212.729616116502946123.3038253784179560.9580917358398440.00010.00.00010.0001505.83002308.857731414.6854103.33906999999999
83822654.00.03698.082.0195.03698.00.06634999999998556195.0195.00.085.729878160142413.978231691978335140.0996856689452850.907897949218750.000100000000000000021.3552527156068802e-200.00010.0001577.7435358.66462119.69586.51878
84832837.00.03881.083.0183.03881.00.036459999999985296183.0183.00.079.9327870463276912.023107460619213113.9982147216796950.351623535156250.00010.00.00010.0001529.7014395.32332509.319893.23408
85843037.00.04081.084.0200.04081.00.01200.0200.00.078.7202673485530713.478753772504628117.5819702148437646.873859405517580.00010.00.00010.0001656.9392443.305662533.294293.711685
86853237.00.04281.085.0200.04281.00.01200.0200.00.080.2828993485800614.76322732790999126.5540237426757839.7211074829101560.00010.00.00010.0001771.22064559.29983551.7788115.3446
87863437.00.04481.086.0200.04481.00.01200.0200.00.076.7059480293312114.472593183429652150.8463439941406241.381271362304690.00010.00.00010.0001810.4775400000001522.28863221.059677.76926999999999
88873637.00.04681.087.0200.04681.00.01200.0200.00.072.9087124158389612.42715688511501115.5774612426757844.612113952636720.00010.00.00010.0001690.33563405.47282354.9749139.82854
89883837.00.04881.088.0200.04881.00.01200.0200.00.073.515186559015814.072884510784956115.2354888916015642.795715332031250.00010.00.00010.0001742.5526519.84412976.320678.22694
90894037.00.05081.089.0200.05081.00.01200.0200.00.068.891467846817713.91539629215193114.3094787597656230.740762710571290.00010.00.00010.0001778.3665499.353153280.32994.1108
91904237.00.05281.090.0200.05281.00.01200.0200.00.069.2158479930168414.63634195328303129.92456054687531.906661987304690.00010.00.00010.0001931.8132300000001627.28124543.6943110.74506000000001
Reference in New Issue View Git Blame Copy Permalink