mirror of
https://github.com/gryf/coach.git
synced 2025-12-29 09:52:31 +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 | 65.0 | 1.0 | 65.0 | 65.0 | 0.5 | 0.0 | |||||||||||||||||
| 3 | 2 | 0.0 | 1.0 | 140.0 | 2.0 | 75.0 | 140.0 | 0.5 | 0.0 | |||||||||||||||||
| 4 | 3 | 0.0 | 1.0 | 187.0 | 3.0 | 47.0 | 187.0 | 0.5 | 0.0 | |||||||||||||||||
| 5 | 4 | 0.0 | 1.0 | 262.0 | 4.0 | 75.0 | 262.0 | 0.5 | 0.0 | |||||||||||||||||
| 6 | 5 | 0.0 | 1.0 | 265.0 | 5.0 | 3.0 | 265.0 | 0.5 | 0.0 | |||||||||||||||||
| 7 | 6 | 0.0 | 1.0 | 277.0 | 6.0 | 12.0 | 277.0 | 0.5 | 0.0 | |||||||||||||||||
| 8 | 7 | 0.0 | 1.0 | 343.0 | 7.0 | 66.0 | 343.0 | 0.5 | 0.0 | |||||||||||||||||
| 9 | 8 | 0.0 | 1.0 | 356.0 | 8.0 | 13.0 | 356.0 | 0.5 | 0.0 | |||||||||||||||||
| 10 | 9 | 0.0 | 1.0 | 366.0 | 9.0 | 10.0 | 366.0 | 0.5 | 0.0 | |||||||||||||||||
| 11 | 10 | 0.0 | 1.0 | 372.0 | 10.0 | 6.0 | 372.0 | 0.5 | 0.0 | |||||||||||||||||
| 12 | 11 | 0.0 | 1.0 | 447.0 | 11.0 | 75.0 | 447.0 | 0.5 | 0.0 | |||||||||||||||||
| 13 | 12 | 0.0 | 1.0 | 452.0 | 12.0 | 5.0 | 452.0 | 0.5 | 0.0 | |||||||||||||||||
| 14 | 13 | 0.0 | 1.0 | 456.0 | 13.0 | 4.0 | 456.0 | 0.5 | 0.0 | |||||||||||||||||
| 15 | 14 | 0.0 | 1.0 | 531.0 | 14.0 | 75.0 | 531.0 | 0.5 | 0.0 | |||||||||||||||||
| 16 | 15 | 0.0 | 1.0 | 535.0 | 15.0 | 4.0 | 535.0 | 0.5 | 0.0 | |||||||||||||||||
| 17 | 16 | 0.0 | 1.0 | 604.0 | 16.0 | 69.0 | 604.0 | 0.5 | 0.0 | |||||||||||||||||
| 18 | 17 | 0.0 | 1.0 | 634.0 | 17.0 | 30.0 | 634.0 | 0.5 | 0.0 | |||||||||||||||||
| 19 | 18 | 0.0 | 1.0 | 709.0 | 18.0 | 75.0 | 709.0 | 0.5 | 0.0 | |||||||||||||||||
| 20 | 19 | 0.0 | 1.0 | 746.0 | 19.0 | 37.0 | 746.0 | 0.5 | 0.0 | |||||||||||||||||
| 21 | 20 | 0.0 | 1.0 | 752.0 | 20.0 | 6.0 | 752.0 | 0.5 | 0.0 | |||||||||||||||||
| 22 | 21 | 0.0 | 1.0 | 761.0 | 21.0 | 9.0 | 761.0 | 0.5 | 0.0 | |||||||||||||||||
| 23 | 22 | 0.0 | 1.0 | 836.0 | 22.0 | 75.0 | 836.0 | 0.5 | 0.0 | |||||||||||||||||
| 24 | 23 | 0.0 | 1.0 | 902.0 | 23.0 | 66.0 | 902.0 | 0.5 | 0.0 | |||||||||||||||||
| 25 | 24 | 0.0 | 1.0 | 905.0 | 24.0 | 3.0 | 905.0 | 0.5 | 0.0 | |||||||||||||||||
| 26 | 25 | 0.0 | 1.0 | 909.0 | 25.0 | 4.0 | 909.0 | 0.5 | 0.0 | |||||||||||||||||
| 27 | 26 | 0.0 | 1.0 | 984.0 | 26.0 | 75.0 | 984.0 | 0.5 | 0.0 | |||||||||||||||||
| 28 | 27 | 0.0 | 1.0 | 993.0 | 27.0 | 9.0 | 993.0 | 0.5 | 0.0 | |||||||||||||||||
| 29 | 28 | 0.0 | 1.0 | 1000.0 | 28.0 | 7.0 | 1000.0 | 0.5 | 0.0 | |||||||||||||||||
| 30 | 29 | 0.0 | 1.0 | 1012.0 | 29.0 | 12.0 | 1012.0 | 0.5 | 0.0 | |||||||||||||||||
| 31 | 30 | 0.0 | 1.0 | 1058.0 | 30.0 | 46.0 | 1058.0 | 0.5 | 0.0 | |||||||||||||||||
| 32 | 31 | 74.0 | 0.0 | 1133.0 | 31.0 | 75.0 | 1133.0 | 0.4962500000000004 | -310.0 | -310.0 | 0.0 | 10044.869384765623 | 5242.989884619314 | 22254.58203125 | 4401.970703125 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 19706.668 | 8858.38 | 54568.945 | 7987.5923 | |||
| 33 | 32 | 149.0 | 0.0 | 1208.0 | 32.0 | 75.0 | 1208.0 | 0.4925000000000008 | -330.0 | -330.0 | 0.0 | 3891.6225783889363 | 637.6236269793292 | 5566.59326171875 | 2664.003662109375 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 8448.435 | 5481.049 | 26043.842 | 2302.9417 | |||
| 34 | 33 | 224.0 | 0.0 | 1283.0 | 33.0 | 75.0 | 1283.0 | 0.4887500000000013 | -350.0 | -350.0 | 0.0 | 3077.779415646115 | 566.1168689908503 | 4660.55615234375 | 1820.854248046875 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 7292.5693 | 4368.0903 | 18343.902 | 1369.8833 | |||
| 35 | 34 | 269.0 | 0.0 | 1328.0 | 34.0 | 45.0 | 1328.0 | 0.4865000000000015 | -107.0 | -107.0 | 0.0 | 2778.7146329012785 | 533.6904650386124 | 3798.990478515625 | 1563.0560302734375 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 7935.2515 | 4627.6504 | 17427.271 | 1315.7484 | |||
| 36 | 35 | 344.0 | 0.0 | 1403.0 | 35.0 | 75.0 | 1403.0 | 0.4827500000000019 | -350.0 | -350.0 | 0.0 | 2548.251075538429 | 503.7895321500006 | 3885.131103515625 | 1336.6544189453125 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 6998.5156 | 3740.0554 | 15615.944 | 1059.72 | |||
| 37 | 36 | 419.0 | 0.0 | 1478.0 | 36.0 | 75.0 | 1478.0 | 0.4790000000000023 | -330.0 | -330.0 | 0.0 | 2403.516982619826 | 544.6621766946007 | 3862.224609375 | 1325.1793212890625 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 9307.738000000001 | 5141.1465 | 26465.752 | 1347.5527 | |||
| 38 | 37 | 494.0 | 0.0 | 1553.0 | 37.0 | 75.0 | 1553.0 | 0.4752500000000027 | -340.0 | -340.0 | 0.0 | 2239.989168734164 | 523.1246187150106 | 3724.3359375 | 1135.0155029296875 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 11598.228000000001 | 7139.8769999999995 | 32025.642999999996 | 1107.6741 | |||
| 39 | 38 | 569.0 | 0.0 | 1628.0 | 38.0 | 75.0 | 1628.0 | 0.4715000000000032 | -340.0 | -340.0 | 0.0 | 2182.150799725507 | 468.15083657342313 | 3649.64501953125 | 1002.2430419921876 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 12550.713 | 7233.5986 | 36740.902 | 1885.9489 | |||
| 40 | 39 | 572.0 | 0.0 | 1631.0 | 39.0 | 3.0 | 1631.0 | 0.4713500000000032 | 91.0 | 91.0 | 0.0 | 2704.028686523437 | 118.6094970703125 | 2822.63818359375 | 2585.419189453125 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 25972.59 | 3807.837 | 29780.428 | 22164.754 | |||
| 41 | 40 | 604.0 | 0.0 | 1663.0 | 40.0 | 32.0 | 1663.0 | 0.4697500000000033 | -45.0 | -45.0 | 0.0 | 1930.68742124496 | 502.9846513531696 | 3201.093017578125 | 1072.453125 | 9.999999999999996e-05 | 4.0657581468206416e-20 | 0.0001 | 0.0001 | 10140.787 | 5985.6997 | 23714.36 | 2408.1848 | |||
| 42 | 41 | 638.0 | 0.0 | 1697.0 | 41.0 | 34.0 | 1697.0 | 0.4680500000000035 | -43.0 | -43.0 | 0.0 | 2243.9218897964015 | 436.8811365455244 | 2995.576416015625 | 1454.529541015625 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 9840.296999999999 | 6234.153 | 22699.38 | 1652.4387 | |||
| 43 | 42 | 713.0 | 0.0 | 1772.0 | 42.0 | 75.0 | 1772.0 | 0.4643000000000039 | -335.0 | -335.0 | 0.0 | 2289.5660070470867 | 429.4154174081929 | 3671.47412109375 | 1392.2723388671875 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 9503.265 | 5894.2974 | 23384.83 | 1498.6058 | |||
| 44 | 43 | 739.0 | 0.0 | 1798.0 | 43.0 | 26.0 | 1798.0 | 0.4630000000000041 | -6.0 | -6.0 | 0.0 | 2134.9425048828125 | 455.004647509431 | 3364.474853515625 | 1390.66064453125 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 9851.771 | 5102.7183 | 21334.49 | 2035.835 | |||
| 45 | 44 | 814.0 | 0.0 | 1873.0 | 44.0 | 75.0 | 1873.0 | 0.4592500000000045 | -315.0 | -315.0 | 0.0 | 2201.6732433422194 | 514.7195921344477 | 3464.29150390625 | 1020.7645874023438 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 8819.354 | 5085.938 | 21895.092 | 1296.8114 | |||
| 46 | 45 | 889.0 | 0.0 | 1948.0 | 45.0 | 75.0 | 1948.0 | 0.4555000000000049 | -345.0 | -345.0 | 0.0 | 2207.215939083615 | 554.4240054132572 | 4052.049072265625 | 1164.0147705078125 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 9008.161 | 5704.8369999999995 | 28084.967 | 1202.0845 | |||
| 47 | 46 | 964.0 | 0.0 | 2023.0 | 46.0 | 75.0 | 2023.0 | 0.4517500000000053 | -335.0 | -335.0 | 0.0 | 2089.54076406118 | 431.9918054466581 | 2953.16748046875 | 1021.1974487304688 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 8598.306 | 4905.4497 | 22985.017999999996 | 1388.7579999999998 | |||
| 48 | 47 | 983.0 | 0.0 | 2042.0 | 47.0 | 19.0 | 2042.0 | 0.4508000000000054 | 17.0 | 17.0 | 0.0 | 2057.0487060546875 | 486.034561988616 | 3028.0859375 | 1063.8616943359377 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 12460.983999999999 | 7062.5854 | 26178.94 | 2331.4316 | |||
| 49 | 48 | 1008.0 | 0.0 | 2067.0 | 48.0 | 25.0 | 2067.0 | 0.4495500000000056 | -22.0 | -22.0 | 0.0 | 2126.609670003256 | 519.2346744619607 | 3212.98486328125 | 1283.1513671875 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 12462.714 | 5630.728 | 23076.666 | 4272.0425 | |||
| 50 | 49 | 1083.0 | 0.0 | 2142.0 | 49.0 | 75.0 | 2142.0 | 0.445800000000006 | -325.0 | -325.0 | 0.0 | 2137.4704177444046 | 463.33556068091485 | 3200.396484375 | 1114.6522216796877 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 11589.511999999999 | 6253.302 | 30283.914 | 1995.5632 | |||
| 51 | 50 | 1111.0 | 0.0 | 2170.0 | 50.0 | 28.0 | 2170.0 | 0.4444000000000061 | -23.0 | -23.0 | 0.0 | 2167.5146213107637 | 418.6486196316667 | 2978.5595703125 | 1144.399169921875 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 10905.161 | 6223.7334 | 30859.734 | 2938.511 | |||
| 52 | 51 | 1125.0 | 0.0 | 2184.0 | 51.0 | 14.0 | 2184.0 | 0.4437000000000062 | 47.0 | 47.0 | 0.0 | 2260.243361253005 | 270.9846229965501 | 2814.1787109375 | 1916.0750732421875 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 10421.190999999999 | 4779.9146 | 18740.24 | 4033.5125 | |||
| 53 | 52 | 1147.0 | 0.0 | 2206.0 | 52.0 | 22.0 | 2206.0 | 0.4426000000000063 | 0.0 | 0.0 | 0.0 | 2312.171648297991 | 431.8343393681421 | 3130.859130859375 | 1384.267822265625 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 10536.329 | 3903.035 | 17744.582 | 2334.9014 | |||
| 54 | 53 | 1222.0 | 0.0 | 2281.0 | 53.0 | 75.0 | 2281.0 | 0.4388500000000067 | -345.0 | -345.0 | 0.0 | 2214.8194217166383 | 490.6178898345874 | 3438.375 | 1277.5692138671875 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 9800.902 | 4857.2 | 25690.402000000002 | 1710.8159 | |||
| 55 | 54 | 1297.0 | 0.0 | 2356.0 | 54.0 | 75.0 | 2356.0 | 0.4351000000000072 | -345.0 | -345.0 | 0.0 | 2152.6272467535896 | 493.85394692218085 | 3566.579833984375 | 1254.210693359375 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 8921.473 | 5468.608 | 22560.812 | 1285.9827 | |||
| 56 | 55 | 1304.0 | 0.0 | 2363.0 | 55.0 | 7.0 | 2363.0 | 0.4347500000000072 | 75.0 | 75.0 | 0.0 | 2388.065470377604 | 576.765661200786 | 3248.211669921875 | 1657.5279541015625 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 10461.333 | 3841.9446 | 13288.776000000002 | 2332.1982 | |||
| 57 | 56 | 1379.0 | 0.0 | 2438.0 | 56.0 | 75.0 | 2438.0 | 0.4310000000000076 | -330.0 | -330.0 | 0.0 | 2083.6998043575804 | 451.0886134002163 | 3321.603759765625 | 1253.80126953125 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 7971.2637 | 4696.2324 | 25760.362999999998 | 1254.4551 | |||
| 58 | 57 | 1381.0 | 0.0 | 2440.0 | 57.0 | 2.0 | 2440.0 | 0.4309000000000076 | 95.0 | 95.0 | 0.0 | 1848.1578369140625 | 0.0 | 1848.1578369140625 | 1848.1578369140625 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 9745.857 | 0.0 | 9745.857 | 9745.857 | |||
| 59 | 58 | 1386.0 | 0.0 | 2445.0 | 58.0 | 5.0 | 2445.0 | 0.4306500000000077 | 76.0 | 76.0 | 0.0 | 2469.050109863281 | 378.86445288616164 | 2849.742431640625 | 2050.549072265625 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 4347.0146 | 1005.71375 | 5272.0645 | 2648.5105 | |||
| 60 | 59 | 1461.0 | 0.0 | 2520.0 | 59.0 | 75.0 | 2520.0 | 0.4269000000000081 | -330.0 | -330.0 | 0.0 | 2129.3425457928633 | 451.2132821428463 | 3655.289794921875 | 1113.34326171875 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 8102.646 | 4872.226 | 22095.9 | 1591.7819 | |||
| 61 | 60 | 1536.0 | 0.0 | 2595.0 | 60.0 | 75.0 | 2595.0 | 0.4231500000000085 | -345.0 | -345.0 | 0.0 | 2085.1278554555533 | 437.58567881234 | 3290.2333984375 | 1268.5421142578125 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 9111.574 | 5091.9233 | 25067.517999999996 | 1348.4824 | |||
| 62 | 61 | 1611.0 | 0.0 | 2670.0 | 61.0 | 75.0 | 2670.0 | 0.4194000000000089 | -350.0 | -350.0 | 0.0 | 2200.5184804555533 | 462.4888624828058 | 3118.872314453125 | 1072.3905029296877 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 11947.702 | 6489.1646 | 25158.611 | 1028.8323 | |||
| 63 | 62 | 1686.0 | 0.0 | 2745.0 | 62.0 | 75.0 | 2745.0 | 0.4156500000000093 | -325.0 | -325.0 | 0.0 | 2026.1754109150654 | 450.22828808801705 | 3065.60986328125 | 987.6249389648438 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 10752.766000000001 | 6122.658 | 27771.957000000002 | 1372.0846 | |||
| 64 | 63 | 1761.0 | 0.0 | 2820.0 | 63.0 | 75.0 | 2820.0 | 0.4119000000000097 | -335.0 | -335.0 | 0.0 | 1894.7486151617927 | 481.5040244992176 | 3235.630126953125 | 915.2020263671876 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 9413.462 | 4855.9287 | 24218.564 | 1202.1124 | |||
| 65 | 64 | 1772.0 | 0.0 | 2831.0 | 64.0 | 11.0 | 2831.0 | 0.41135000000000976 | 49.0 | 49.0 | 0.0 | 1993.5283447265624 | 453.2569012371 | 3084.971435546875 | 1584.0709228515625 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 8501.79 | 4672.495 | 16319.774 | 3136.5254 | |||
| 66 | 65 | 1784.0 | 0.0 | 2843.0 | 65.0 | 12.0 | 2843.0 | 0.4107500000000098 | 38.0 | 38.0 | 0.0 | 1816.0982111150568 | 312.48056576674486 | 2356.739990234375 | 1309.124755859375 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 11706.223999999998 | 6139.613 | 21345.24 | 3042.6313 |