mirror of
https://github.com/gryf/coach.git
synced 2026-01-27 02:25:45 +01:00
* 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
10 KiB
10 KiB
| 1 | Episode # | Training Iter | In Heatup | ER #Transitions | ER #Episodes | Episode Length | Total steps | Epsilon | Shaped Training Reward | Training Reward | Update Target Network | Evaluation Reward | Shaped Evaluation Reward | Success Rate | Loss/Mean | Loss/Stdev | Loss/Max | Loss/Min | Learning Rate/Mean | Learning Rate/Stdev | Learning Rate/Max | Learning Rate/Min | Grads (unclipped)/Mean | Grads (unclipped)/Stdev | Grads (unclipped)/Max | Grads (unclipped)/Min |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 1 | 0.0 | 1.0 | 72.0 | 1.0 | 72.0 | 72.0 | 1.0 | 0.0 | |||||||||||||||||
| 3 | 2 | 0.0 | 1.0 | 152.0 | 2.0 | 80.0 | 152.0 | 1.0 | 0.0 | |||||||||||||||||
| 4 | 3 | 0.0 | 1.0 | 258.0 | 3.0 | 106.0 | 258.0 | 1.0 | 0.0 | |||||||||||||||||
| 5 | 4 | 0.0 | 1.0 | 395.0 | 4.0 | 137.0 | 395.0 | 1.0 | 0.0 | |||||||||||||||||
| 6 | 5 | 0.0 | 1.0 | 482.0 | 5.0 | 87.0 | 482.0 | 1.0 | 0.0 | |||||||||||||||||
| 7 | 6 | 0.0 | 1.0 | 619.0 | 6.0 | 137.0 | 619.0 | 1.0 | 0.0 | |||||||||||||||||
| 8 | 7 | 0.0 | 1.0 | 741.0 | 7.0 | 122.0 | 741.0 | 1.0 | 0.0 | |||||||||||||||||
| 9 | 8 | 0.0 | 1.0 | 854.0 | 8.0 | 113.0 | 854.0 | 1.0 | 0.0 | |||||||||||||||||
| 10 | 9 | 0.0 | 1.0 | 990.0 | 9.0 | 136.0 | 990.0 | 1.0 | 0.0 | |||||||||||||||||
| 11 | 10 | 0.0 | 1.0 | 1156.0 | 10.0 | 166.0 | 1156.0 | 1.0 | 0.0 | |||||||||||||||||
| 12 | 11 | 11.0 | 0.0 | 1244.0 | 11.0 | 88.0 | 1244.0 | 0.9999926666666656 | 1.0 | 1.0 | 0.0 | 1362870.1704545454 | 202633.285804588 | 1791029.375 | 1155478.75 | 9.999999e-05 | 7.275958000000001e-12 | 0.0001 | 0.0001 | 9181.704 | 4671.3325 | 16804.215 | 2813.8562 | |||
| 13 | 12 | 36.0 | 0.0 | 1441.0 | 12.0 | 197.0 | 1441.0 | 0.9999762499999968 | 0.0 | 0.0 | 0.0 | 1268819.7825 | 170348.8094881748 | 1559968.75 | 883666.875 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 92217.93 | 58346.1 | 230842.81 | 21415.611 | |||
| 14 | 13 | 59.0 | 0.0 | 1625.0 | 13.0 | 184.0 | 1625.0 | 0.9999609166666612 | 3.0 | 3.0 | 0.0 | 1097453.4375 | 185885.35478564832 | 1374968.875 | 690323.5625 | 0.000100000005 | 7.275958000000001e-12 | 0.0001 | 0.0001 | 450407.75 | 199749.47 | 1067648.8 | 161257.92 | |||
| 15 | 14 | 73.0 | 0.0 | 1737.0 | 14.0 | 112.0 | 1737.0 | 0.9999515833333266 | 1.0 | 1.0 | 0.0 | 720170.7767857143 | 82766.57804747311 | 925555.75 | 584423.0625 | 9.999997999999999e-05 | 1.4551915e-11 | 0.0001 | 0.0001 | 590398.1 | 221381.36 | 1045701.94 | 173675.36 | |||
| 16 | 15 | 80.0 | 0.0 | 1791.0 | 15.0 | 54.0 | 1791.0 | 0.999947083333326 | 0.0 | 0.0 | 0.0 | 793692.9196428572 | 183183.90341960813 | 1169408.625 | 528233.0 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 528360.7 | 289105.4 | 1114415.6 | 242876.17 | |||
| 17 | 16 | 90.0 | 0.0 | 1871.0 | 16.0 | 80.0 | 1871.0 | 0.9999404166666584 | 1.0 | 1.0 | 0.0 | 694066.5 | 88371.25598764779 | 864256.125 | 549745.5625 | 9.999999e-05 | 7.275958000000001e-12 | 0.0001 | 0.0001 | 818027.9 | 296357.25 | 1396105.4 | 287447.03 | |||
| 18 | 17 | 102.0 | 0.0 | 1967.0 | 17.0 | 96.0 | 1967.0 | 0.9999324166666572 | 0.0 | 0.0 | 0.0 | 663839.9739583335 | 64899.01893068695 | 784205.3125 | 579032.4375 | 9.999997999999999e-05 | 1.4551915e-11 | 0.0001 | 0.0001 | 462420.34 | 251265.42 | 1030484.4 | 147935.28 | |||
| 19 | 18 | 110.0 | 0.0 | 2032.0 | 18.0 | 65.0 | 2032.0 | 0.9999269999999898 | 1.0 | 1.0 | 0.0 | 695984.3046875 | 84768.39021610889 | 807562.3125 | 547180.125 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 430391.94 | 207812.47 | 813183.8 | 207811.73 | |||
| 20 | 19 | 116.0 | 0.0 | 2085.0 | 19.0 | 53.0 | 2085.0 | 0.9999225833333224 | 0.0 | 0.0 | 0.0 | 673908.1041666665 | 77784.40400788287 | 775135.0 | 553173.125 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 442691.22 | 271139.0 | 958457.1 | 166330.6 | |||
| 21 | 20 | 128.0 | 0.0 | 2180.0 | 20.0 | 95.0 | 2180.0 | 0.9999146666666548 | 2.0 | 2.0 | 0.0 | 711864.0284090909 | 61660.675056842 | 830183.75 | 627056.3125 | 9.999999e-05 | 7.275958000000001e-12 | 0.0001 | 0.0001 | 329869.97 | 199046.1 | 782139.25 | 134099.55 | |||
| 22 | 21 | 134.0 | 0.0 | 2225.0 | 21.0 | 45.0 | 2225.0 | 0.9999109166666542 | 0.0 | 0.0 | 0.0 | 756522.7291666665 | 88243.27123964629 | 866818.375 | 639968.4375 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 325175.53 | 284253.2 | 944805.1 | 95649.45 | |||
| 23 | 22 | 148.0 | 0.0 | 2337.0 | 22.0 | 112.0 | 2337.0 | 0.9999015833333196 | 1.0 | 1.0 | 0.0 | 753146.6071428572 | 115219.81685904574 | 973936.4375 | 540484.1875 | 9.999997999999999e-05 | 1.4551915e-11 | 0.0001 | 0.0001 | 352548.53 | 180664.31 | 817212.75 | 144533.8 | |||
| 24 | 23 | 170.0 | 0.0 | 2514.0 | 23.0 | 177.0 | 2514.0 | 0.9998868333333176 | 0.0 | 0.0 | 0.0 | 749934.375 | 127832.68941495092 | 1075921.25 | 560355.1875 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 439716.4 | 199622.05 | 805644.3 | 94781.4 | |||
| 25 | 24 | 180.0 | 0.0 | 2597.0 | 24.0 | 83.0 | 2597.0 | 0.99987991666665 | 1.0 | 1.0 | 0.0 | 681247.534375 | 125400.85689817193 | 912867.6875 | 479958.875 | 9.999999e-05 | 7.275958000000001e-12 | 0.0001 | 0.0001 | 449936.8 | 239054.84 | 869260.4 | 148829.58 | |||
| 26 | 25 | 197.0 | 0.0 | 2730.0 | 25.0 | 133.0 | 2730.0 | 0.999868833333315 | 0.0 | 0.0 | 0.0 | 754226.9609375 | 110542.87950780631 | 983924.6875 | 558276.25 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 394444.8 | 215846.53 | 802207.56 | 85587.93 | |||
| 27 | 26 | 215.0 | 0.0 | 2877.0 | 26.0 | 147.0 | 2877.0 | 0.9998565833333132 | 0.0 | 0.0 | 0.0 | 719173.9565972221 | 144825.75469796525 | 1032319.25 | 475236.03125 | 9.999999e-05 | 7.275958000000001e-12 | 0.0001 | 0.0001 | 388564.3 | 249133.19 | 877856.56 | 109499.53 | |||
| 28 | 27 | 222.0 | 0.0 | 2928.0 | 27.0 | 51.0 | 2928.0 | 0.9998523333333128 | 0.0 | 0.0 | 0.0 | 731635.703125 | 157399.60955146723 | 985211.8125 | 485650.28125 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 301588.4 | 73236.35 | 434868.34 | 221974.97 | |||
| 29 | 28 | 234.0 | 0.0 | 3024.0 | 28.0 | 96.0 | 3024.0 | 0.9998443333333116 | 0.0 | 0.0 | 0.0 | 673434.9453125 | 111291.97425632774 | 879607.4375 | 452086.28125 | 9.999997999999999e-05 | 1.4551915e-11 | 0.0001 | 0.0001 | 440101.47 | 281616.66 | 983453.8 | 84773.36 | |||
| 30 | 29 | 253.0 | 0.0 | 3181.0 | 29.0 | 157.0 | 3181.0 | 0.9998312499999764 | 1.0 | 1.0 | 0.0 | 744315.5394736843 | 86624.83914007386 | 875519.125 | 577295.25 | 9.999999e-05 | 7.275958000000001e-12 | 0.0001 | 0.0001 | 458807.78 | 282635.44 | 1082215.9 | 131421.58 | |||
| 31 | 30 | 267.0 | 0.0 | 3286.0 | 30.0 | 105.0 | 3286.0 | 0.9998224999999752 | 1.0 | 1.0 | 0.0 | 717434.2548076924 | 115258.97615360047 | 923873.5625 | 543786.4375 | 9.999997999999999e-05 | 1.4551915e-11 | 0.0001 | 0.0001 | 428558.7 | 207691.47 | 811162.75 | 130643.875 | |||
| 32 | 31 | 277.0 | 0.0 | 3366.0 | 31.0 | 80.0 | 3366.0 | 0.9998158333333076 | 0.0 | 0.0 | 0.0 | 711374.3125 | 72415.09235334143 | 849278.8125 | 601717.375 | 9.999999e-05 | 7.275958000000001e-12 | 0.0001 | 0.0001 | 378304.38 | 286992.25 | 1077769.1 | 67283.75 | |||
| 33 | 32 | 300.0 | 0.0 | 3550.0 | 32.0 | 184.0 | 3550.0 | 0.999800499999972 | 0.0 | 0.0 | 0.0 | 698363.5326086957 | 112767.16092423502 | 921901.75 | 502200.0 | 0.000100000005 | 7.275958000000001e-12 | 0.0001 | 0.0001 | 431487.66 | 306761.94 | 1354223.5 | 84960.38 | |||
| 34 | 33 | 308.0 | 0.0 | 3620.0 | 33.0 | 70.0 | 3620.0 | 0.999794666666638 | 0.0 | 0.0 | 0.0 | 663993.609375 | 87096.32117536859 | 766391.0625 | 544220.25 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 375039.7 | 253182.45 | 942774.4 | 98368.99 | |||
| 35 | 34 | 321.0 | 0.0 | 3718.0 | 34.0 | 98.0 | 3718.0 | 0.9997864999999702 | 2.0 | 2.0 | 0.0 | 765584.3293269231 | 128695.47134763454 | 1029789.8125 | 470668.53125 | 9.999997999999999e-05 | 1.4551915e-11 | 0.0001 | 0.0001 | 441566.94 | 373265.66 | 1470760.2 | 87515.73 | |||
| 36 | 35 | 338.0 | 0.0 | 3859.0 | 35.0 | 141.0 | 3859.0 | 0.9997747499999684 | 0.0 | 0.0 | 0.0 | 716884.143382353 | 131576.0497345416 | 1011837.1875 | 506844.59375 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 373415.72 | 231345.11 | 874751.0 | 113355.9 | |||
| 37 | 36 | 355.0 | 0.0 | 3995.0 | 36.0 | 136.0 | 3995.0 | 0.9997634166666336 | 0.0 | 0.0 | 0.0 | 721937.2352941177 | 103882.59283400288 | 882992.0625 | 531336.25 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 382764.12 | 213119.66 | 774643.94 | 99552.88 | |||
| 38 | 37 | 371.0 | 0.0 | 4119.0 | 37.0 | 124.0 | 4119.0 | 0.9997530833332988 | 2.0 | 2.0 | 0.0 | 725186.1640625 | 100878.22357900153 | 903022.8125 | 549947.1875 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 344175.0 | 232836.8 | 1010777.3 | 94721.695 | |||
| 39 | 38 | 385.0 | 0.0 | 4235.0 | 38.0 | 116.0 | 4235.0 | 0.9997434166666308 | 0.0 | 0.0 | 0.0 | 719966.3928571428 | 107142.55067114241 | 892775.0625 | 559991.0625 | 9.999997999999999e-05 | 1.4551915e-11 | 0.0001 | 0.0001 | 362664.7 | 240388.1 | 850150.8 | 97869.42 | |||
| 40 | 39 | 393.0 | 0.0 | 4294.0 | 39.0 | 59.0 | 4294.0 | 0.9997384999999634 | 1.0 | 1.0 | 0.0 | 666581.046875 | 59949.999658127774 | 763241.4375 | 564228.375 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 358627.62 | 161667.34 | 674228.06 | 161123.34 | |||
| 41 | 40 | 406.0 | 0.0 | 4404.0 | 40.0 | 110.0 | 4404.0 | 0.9997293333332956 | 1.0 | 1.0 | 0.0 | 709309.3269230769 | 102515.23694020779 | 971747.5625 | 537066.0 | 9.999997999999999e-05 | 1.4551915e-11 | 0.0001 | 0.0001 | 408076.66 | 251145.9 | 939021.3 | 135196.75 | |||
| 42 | 41 | 419.0 | 0.0 | 4504.0 | 41.0 | 100.0 | 4504.0 | 0.999720999999961 | 0.0 | 0.0 | 0.0 | 686281.7019230769 | 90042.421657481 | 842031.3125 | 527866.875 | 9.999997999999999e-05 | 1.4551915e-11 | 0.0001 | 0.0001 | 338762.03 | 148208.45 | 606126.94 | 76600.88 | |||
| 43 | 42 | 429.0 | 0.0 | 4584.0 | 42.0 | 80.0 | 4584.0 | 0.9997143333332934 | 3.0 | 3.0 | 0.0 | 694091.75625 | 127169.41574577989 | 1005687.0 | 532953.9375 | 9.999999e-05 | 7.275958000000001e-12 | 0.0001 | 0.0001 | 329838.75 | 252700.66 | 1017597.1 | 130741.94 | |||
| 44 | 43 | 442.0 | 0.0 | 4689.0 | 43.0 | 105.0 | 4689.0 | 0.9997055833332922 | 1.0 | 1.0 | 0.0 | 732414.8461538461 | 105516.87352287804 | 938344.8125 | 593771.4375 | 9.999997999999999e-05 | 1.4551915e-11 | 0.0001 | 0.0001 | 484232.2 | 309624.44 | 1061726.0 | 131808.27 | |||
| 45 | 44 | 447.0 | 0.0 | 4726.0 | 44.0 | 37.0 | 4726.0 | 0.9997024999999584 | 0.0 | 0.0 | 0.0 | 621613.64375 | 88833.6735713408 | 766784.0 | 523614.59375 | 9.999999e-05 | 7.275958000000001e-12 | 0.0001 | 0.0001 | 451280.84 | 370993.25 | 980591.94 | 93973.31 | |||
| 46 | 45 | 459.0 | 0.0 | 4827.0 | 45.0 | 101.0 | 4827.0 | 0.9996940833332906 | 1.0 | 1.0 | 0.0 | 680325.484375 | 72351.88512190571 | 792630.5625 | 526941.5 | 9.999997999999999e-05 | 1.4551915e-11 | 0.0001 | 0.0001 | 378972.03 | 195156.19 | 840612.44 | 107550.62 | |||
| 47 | 46 | 469.0 | 0.0 | 4905.0 | 46.0 | 78.0 | 4905.0 | 0.9996875833332896 | 3.0 | 3.0 | 0.0 | 744519.775 | 99203.81398693724 | 880234.1875 | 557504.8125 | 9.999999e-05 | 7.275958000000001e-12 | 0.0001 | 0.0001 | 824161.1 | 564658.56 | 2085172.5 | 121570.23 | |||
| 48 | 47 | 495.0 | 0.0 | 5117.0 | 47.0 | 212.0 | 5117.0 | 0.9996699166666204 | 1.0 | 1.0 | 0.0 | 666839.3653846154 | 118226.9086615851 | 998517.9375 | 479699.1875 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 460829.7 | 307543.2 | 1244141.6 | 121380.04 | |||
| 49 | 48 | 512.0 | 0.0 | 5246.0 | 48.0 | 129.0 | 5246.0 | 0.999659166666619 | 3.0 | 3.0 | 0.0 | 724131.26171875 | 104821.64083994547 | 912557.0 | 523902.9375 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 473582.8 | 269440.06 | 852397.56 | 92651.44 | |||
| 50 | 49 | 523.0 | 0.0 | 5340.0 | 49.0 | 94.0 | 5340.0 | 0.9996513333332846 | 1.0 | 1.0 | 0.0 | 677181.9005681818 | 113756.40176243836 | 792532.8125 | 446570.09375 | 9.999999e-05 | 7.275958000000001e-12 | 0.0001 | 0.0001 | 426151.6 | 275540.97 | 982115.75 | 162091.97 | |||
| 51 | 50 | 541.0 | 0.0 | 5483.0 | 50.0 | 143.0 | 5483.0 | 0.9996394166666164 | 0.0 | 0.0 | 0.0 | 656404.2326388889 | 89892.79274772826 | 839570.625 | 455081.8125 | 9.999999e-05 | 7.275958000000001e-12 | 0.0001 | 0.0001 | 372426.47 | 180298.83 | 759154.75 | 102154.5 | |||
| 52 | 51 | 566.0 | 0.0 | 5679.0 | 51.0 | 196.0 | 5679.0 | 0.9996230833332806 | 1.0 | 1.0 | 0.0 | 684399.3525 | 71293.6438434751 | 844978.75 | 550241.9375 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 377658.4 | 249473.56 | 1174649.4 | 101264.086 | |||
| 53 | 52 | 577.0 | 0.0 | 5770.0 | 52.0 | 91.0 | 5770.0 | 0.9996154999999464 | 0.0 | 0.0 | 0.0 | 734663.8295454546 | 138708.0628225473 | 971894.75 | 556492.8125 | 9.999999e-05 | 7.275958000000001e-12 | 0.0001 | 0.0001 | 495256.12 | 317518.9 | 1112388.5 | 122531.75 | |||
| 54 | 53 | 589.0 | 0.0 | 5862.0 | 53.0 | 92.0 | 5862.0 | 0.9996078333332784 | 0.0 | 0.0 | 0.0 | 738314.2708333335 | 104967.43094615475 | 975733.9375 | 635852.5 | 9.999997999999999e-05 | 1.4551915e-11 | 0.0001 | 0.0001 | 430747.12 | 268599.2 | 1025506.25 | 80480.11 | |||
| 55 | 54 | 600.0 | 0.0 | 5952.0 | 54.0 | 90.0 | 5952.0 | 0.9996003333332776 | 1.0 | 1.0 | 0.0 | 733725.8863636364 | 120333.56674581894 | 946715.4375 | 519085.5 | 9.999999e-05 | 7.275958000000001e-12 | 0.0001 | 0.0001 | 422559.28 | 226174.39 | 902062.06 | 185472.72 | |||
| 56 | 55 | 620.0 | 0.0 | 6117.0 | 55.0 | 165.0 | 6117.0 | 0.9995865833332755 | 2.0 | 2.0 | 0.0 | 678218.7921875 | 109486.55792635801 | 881090.875 | 486249.4375 | 9.999999e-05 | 7.275958000000001e-12 | 0.0001 | 0.0001 | 367297.9 | 191436.94 | 823213.56 | 87477.06 |