mirror of
https://github.com/gryf/coach.git
synced 2026-02-14 12:55:51 +01:00
7.8 KiB
7.8 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 | Q/Mean | Q/Stdev | Q/Max | Q/Min |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 1 | 0.0 | 1.0 | 486.0 | 486.0 | 486.0 | 486.0 | 1.0 | 0.0 | |||||||||||||||||||||
| 3 | 2 | 0.0 | 1.0 | 573.0 | 573.0 | 87.0 | 573.0 | 1.0 | 0.0 | |||||||||||||||||||||
| 4 | 3 | 0.0 | 1.0 | 722.0 | 722.0 | 149.0 | 722.0 | 1.0 | 0.0 | |||||||||||||||||||||
| 5 | 4 | 0.0 | 1.0 | 1057.0 | 1057.0 | 335.0 | 1057.0 | 1.0 | 0.0 | |||||||||||||||||||||
| 6 | 5 | 51.0 | 0.0 | 1260.0 | 1260.0 | 203.0 | 1260.0 | 0.9997990300000044 | 3.0 | 30.0 | 0.0 | 0.00940180963759 | 0.013470017241472877 | 0.049212761223316186 | 7.353317050728947e-05 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.05542052 | 0.04357862 | 0.2064145 | 0.0068079852 | |||||||
| 7 | 6 | 116.0 | 0.0 | 1519.0 | 1519.0 | 259.0 | 1519.0 | 0.99954262000001 | 3.0 | 30.0 | 0.0 | 0.00929965893737972 | 0.0103402052036756 | 0.043653115630149834 | 0.00013044019578956068 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.05437565 | 0.029937742000000003 | 0.16640274 | 0.014032418 | |||||||
| 8 | 7 | 154.0 | 0.0 | 1673.0 | 1673.0 | 154.0 | 1673.0 | 0.9993901600000132 | 0.0 | 0.0 | 0.0 | 0.006740736214085605 | 0.0077994245669990815 | 0.02814924158155918 | 0.00014988234033808112 | 9.999999999999998e-05 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.04434246 | 0.024655161000000002 | 0.10726423 | 0.009831297 | |||||||
| 9 | 8 | 188.0 | 0.0 | 1809.0 | 1809.0 | 136.0 | 1809.0 | 0.9992555200000162 | 0.0 | 0.0 | 0.0 | 0.005733611607437897 | 0.009189231003716951 | 0.030967287719249725 | 0.00016953394515439868 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.043634683 | 0.030018644 | 0.13496692 | 0.013218384 | |||||||
| 10 | 9 | 218.0 | 0.0 | 1927.0 | 1927.0 | 118.0 | 1927.0 | 0.9991387000000188 | 4.0 | 50.0 | 0.0 | 0.005415936872547415 | 0.008556929403770156 | 0.02886312827467918 | 9.317453077528626e-05 | 9.999999999999998e-05 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.034520287000000004 | 0.032297213 | 0.1215473 | 0.005115339 | |||||||
| 11 | 10 | 239.0 | 0.0 | 2013.0 | 2013.0 | 86.0 | 2013.0 | 0.9990535600000204 | 1.0 | 25.0 | 0.0 | 0.0070035762688522 | 0.010885615572279907 | 0.04120698943734169 | 0.00020946483709849417 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.04824697 | 0.030201659 | 0.14718142 | 0.011774496 | |||||||
| 12 | 11 | 285.0 | 0.0 | 2197.0 | 2197.0 | 184.0 | 2197.0 | 0.9988714000000244 | 5.0 | 75.0 | 0.0 | 0.004890300252357164 | 0.008976665125631113 | 0.04363592341542244 | 6.938744627404958e-05 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.036006905 | 0.034595415 | 0.17641488 | 0.006081335699999999 | |||||||
| 13 | 12 | 309.0 | 0.0 | 2293.0 | 2293.0 | 96.0 | 2293.0 | 0.9987763600000266 | 2.0 | 15.0 | 0.0 | 0.005085365288929704 | 0.007954596864360095 | 0.02850999496877193 | 0.00011609210923779756 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.03620706 | 0.029377367 | 0.12884642 | 0.008971761 | |||||||
| 14 | 13 | 353.0 | 0.0 | 2467.0 | 2467.0 | 174.0 | 2467.0 | 0.9986041000000304 | 2.0 | 35.0 | 0.0 | 0.004483388394212604 | 0.00714934797623927 | 0.02857648953795433 | 0.00013717712135985494 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.036266383 | 0.027188765 | 0.13212168 | 0.007937131 | |||||||
| 15 | 14 | 400.0 | 0.0 | 2658.0 | 2658.0 | 191.0 | 2658.0 | 0.9984150100000344 | 1.0 | 25.0 | 0.0 | 0.009708599779418016 | 0.010096475736274924 | 0.02948019653558731 | 0.0001457566395401955 | 0.00010000000000000003 | 4.0657581468206416e-20 | 0.0001 | 0.0001 | 0.057232287 | 0.02955401 | 0.11976757 | 0.009687495 | 0.020525673 | 0.022543962999999997 | 0.057359524 | -0.00018235296000000003 | |||
| 16 | 15 | 420.0 | 0.0 | 2737.0 | 2737.0 | 79.0 | 2737.0 | 0.998336800000036 | 3.0 | 30.0 | 0.0 | 0.00882622374338098 | 0.0091420211364319 | 0.0285559706389904 | 0.00018760087550617757 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.057375748 | 0.026795514 | 0.13112505 | 0.0137673 | |||||||
| 17 | 16 | 441.0 | 0.0 | 2822.0 | 2822.0 | 85.0 | 2822.0 | 0.998252650000038 | 1.0 | 20.0 | 0.0 | 0.011031260833122012 | 0.009569946432597565 | 0.03008048608899116 | 0.00048281182534992695 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.05970306 | 0.02625892 | 0.12840712 | 0.033901475 | |||||||
| 18 | 17 | 497.0 | 0.0 | 3045.0 | 3045.0 | 223.0 | 3045.0 | 0.9980318800000428 | 2.0 | 30.0 | 0.0 | 0.008167038722084336 | 0.010402760976485893 | 0.04138598218560219 | 0.00016764989413786682 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.05264644 | 0.031224351 | 0.15228507 | 0.009589122 | 0.031049637 | 0.017366769 | 0.054128982 | 0.008472132 | |||
| 19 | 18 | 519.0 | 0.0 | 3133.0 | 3133.0 | 88.0 | 3133.0 | 0.9979447600000446 | 1.0 | 10.0 | 0.0 | 0.007431875651739327 | 0.008212131171736225 | 0.02906158193945885 | 0.00022462599736172706 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.047143605 | 0.022326201 | 0.102964535 | 0.011409067 | |||||||
| 20 | 19 | 586.0 | 0.0 | 3399.0 | 3399.0 | 266.0 | 3399.0 | 0.9976814200000504 | 1.0 | 15.0 | 0.0 | 0.006048565374039211 | 0.00959834709079883 | 0.04419469088315964 | 0.000143644108902663 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.04074958 | 0.03353222 | 0.17308132 | 0.007977235 | |||||||
| 21 | 20 | 644.0 | 0.0 | 3631.0 | 3631.0 | 232.0 | 3631.0 | 0.9974517400000552 | 3.0 | 30.0 | 0.0 | 0.007784245730425906 | 0.009337813281732395 | 0.028873851522803307 | 9.985487849917264e-05 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.04649539 | 0.027173713 | 0.10975073 | 0.009595879 | 0.027574325 | 0.011750318000000001 | 0.04569574 | 0.007722944 | |||
| 22 | 21 | 691.0 | 0.0 | 3822.0 | 3822.0 | 191.0 | 3822.0 | 0.9972626500000594 | 1.0 | 5.0 | 0.0 | 0.006470101633780398 | 0.010489537703026445 | 0.05461757257580757 | 0.00014083684072829786 | 0.00010000000000000003 | 4.0657581468206416e-20 | 0.0001 | 0.0001 | 0.0441633 | 0.039446674 | 0.23385541 | 0.009449824 | 0.01200008 | 0.022514707999999998 | 0.05078985 | -0.017729387 | |||
| 23 | 22 | 763.0 | 0.0 | 4110.0 | 4110.0 | 288.0 | 4110.0 | 0.9969775300000656 | 5.0 | 100.0 | 0.0 | 0.0066310648020993955 | 0.009575129646368427 | 0.04328501597046852 | 0.00016888145182747394 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.04513968 | 0.031045547000000003 | 0.16462055 | 0.010064708 | 0.04988414 | 0.011430293999999999 | 0.064003214 | 0.036855176 | |||
| 24 | 23 | 809.0 | 0.0 | 4291.0 | 4291.0 | 181.0 | 4291.0 | 0.9967983400000696 | 2.0 | 15.0 | 0.0 | 0.006861102552489761 | 0.010954410291041149 | 0.05771709606051445 | 0.00012457562843337655 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.04564552400000001 | 0.03979948 | 0.23009126 | 0.0074085719999999996 | |||||||
| 25 | 24 | 832.0 | 0.0 | 4384.0 | 4384.0 | 93.0 | 4384.0 | 0.9967062700000716 | 2.0 | 15.0 | 0.0 | 0.008675283397441608 | 0.008623302078703028 | 0.027513300999999046 | 0.00015699448704253882 | 9.999999999999998e-05 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.05430378 | 0.026372662 | 0.11436402 | 0.009731605 | |||||||
| 26 | 25 | 896.0 | 0.0 | 4639.0 | 4639.0 | 255.0 | 4639.0 | 0.996453820000077 | 3.0 | 50.0 | 0.0 | 0.0054938030840503424 | 0.007638551486072099 | 0.02796961739659309 | 8.068231545621529e-05 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.037935376 | 0.02827963 | 0.11181499 | 0.005339783000000001 | 0.004497289 | 0.018064981 | 0.040434074 | -0.019658553999999998 | |||
| 27 | 26 | 947.0 | 0.0 | 4846.0 | 4846.0 | 207.0 | 4846.0 | 0.9962488900000814 | 1.0 | 25.0 | 0.0 | 0.0044717073599481495 | 0.007082276129211859 | 0.029280548915266987 | 7.399438618449493e-05 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.03497283 | 0.025866767000000002 | 0.09855921599999999 | 0.00447959 | |||||||
| 28 | 27 | 963.0 | 0.0 | 4909.0 | 4909.0 | 63.0 | 4909.0 | 0.9961865200000828 | 2.0 | 15.0 | 0.0 | 0.008858921806677245 | 0.01043667351261243 | 0.027657225728034973 | 0.00016564546967856586 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.056215905 | 0.030125381 | 0.11781071 | 0.014718769 | |||||||
| 29 | 28 | 982.0 | 0.0 | 4985.0 | 4985.0 | 76.0 | 4985.0 | 0.9961112800000844 | 0.0 | 0.0 | 0.0 | 0.0062713482873636844 | 0.007616313665533986 | 0.027278902009129524 | 0.00024076526460703462 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.043400805 | 0.02980698 | 0.13167736 | 0.012277668 | |||||||
| 30 | 29 | 1048.0 | 0.0 | 5247.0 | 5247.0 | 262.0 | 5247.0 | 0.99585190000009 | 3.0 | 30.0 | 0.0 | 0.004862750120523604 | 0.008166937115952044 | 0.043642010539770126 | 9.04020926100202e-05 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.036356255 | 0.030857606 | 0.17419964 | 0.0053508769999999995 | 0.007745307 | 0.011687581 | 0.0191111 | -0.012445831999999999 | |||
| 31 | 30 | 1108.0 | 0.0 | 5487.0 | 5487.0 | 240.0 | 5487.0 | 0.9956143000000952 | 2.0 | 45.0 | 0.0 | 0.0061263717832237795 | 0.008292486975753062 | 0.030202906578779217 | 9.224841778632252e-05 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.040730584 | 0.029142 | 0.12726964 | 0.0064920974 |