mirror of
https://github.com/gryf/coach.git
synced 2026-01-28 02:55:46 +01:00
6.4 KiB
6.4 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 | 0.009506131430480666 | 0.013357074931555628 | 0.04922456666827202 | 0.00011823583918157964 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.04541644 | 0.032187756 | 0.13184725 | 0.008537644 | |||||||
| 7 | 6 | 116.0 | 0.0 | 1519.0 | 1519.0 | 259.0 | 1519.0 | 0.99954262000001 | 3.0 | 30.0 | 0.0 | 0.009436892453007974 | 0.010444927167927037 | 0.044396519660949714 | 0.0002187119680456817 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.043486382999999997 | 0.028469712999999997 | 0.1315432 | 0.010239484 | |||||||
| 8 | 7 | 154.0 | 0.0 | 1673.0 | 1673.0 | 154.0 | 1673.0 | 0.9993901600000132 | 0.0 | 0.0 | 0.0 | 0.006680036455739021 | 0.007691341664224352 | 0.028086043894290924 | 0.00016294234956149012 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.03525371 | 0.022364777000000002 | 0.08392369999999999 | 0.009258808 | |||||||
| 9 | 8 | 188.0 | 0.0 | 1809.0 | 1809.0 | 136.0 | 1809.0 | 0.9992555200000162 | 0.0 | 0.0 | 0.0 | 0.005725367511759567 | 0.009134182509519568 | 0.030434217303991318 | 0.0001105146948248148 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.031003432 | 0.026752787000000004 | 0.11063196 | 0.008286015 | |||||||
| 10 | 9 | 218.0 | 0.0 | 1927.0 | 1927.0 | 118.0 | 1927.0 | 0.9991387000000188 | 4.0 | 50.0 | 0.0 | 0.005530147604683104 | 0.008635781810203545 | 0.029109837487339973 | 0.00016355639672838151 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.026989017 | 0.024766427 | 0.08535746 | 0.006113700600000001 | |||||||
| 11 | 10 | 239.0 | 0.0 | 2013.0 | 2013.0 | 86.0 | 2013.0 | 0.9990535600000204 | 1.0 | 25.0 | 0.0 | 0.007073877079944525 | 0.010856981851779086 | 0.040930863469839096 | 0.00027058221166953444 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.03715521 | 0.026002409 | 0.11184523 | 0.0153889125 | |||||||
| 12 | 11 | 285.0 | 0.0 | 2197.0 | 2197.0 | 184.0 | 2197.0 | 0.9988714000000244 | 5.0 | 75.0 | 0.0 | 0.0049696794215022865 | 0.008980699602831191 | 0.043269582092761986 | 0.00012109361705370249 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.025901955 | 0.02628609 | 0.11205949 | 0.006279965 | |||||||
| 13 | 12 | 309.0 | 0.0 | 2293.0 | 2293.0 | 96.0 | 2293.0 | 0.9987763600000266 | 2.0 | 15.0 | 0.0 | 0.005058763722142127 | 0.007785021317331955 | 0.027659159153699875 | 0.00018030928913503885 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.027570038999999998 | 0.021486067999999997 | 0.08631482 | 0.008357895 | |||||||
| 14 | 13 | 353.0 | 0.0 | 2467.0 | 2467.0 | 174.0 | 2467.0 | 0.9986041000000304 | 2.0 | 35.0 | 0.0 | 0.0045628238068192405 | 0.007280793903160444 | 0.028272464871406555 | 9.907802450470626e-05 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.025343232 | 0.02227741 | 0.07953325 | 0.0048882863 | |||||||
| 15 | 14 | 400.0 | 0.0 | 2658.0 | 2658.0 | 191.0 | 2658.0 | 0.9984150100000344 | 1.0 | 25.0 | 0.0 | 0.0097321032195357 | 0.01023961919664894 | 0.030154820531606674 | 0.00018444313900545242 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.04259975 | 0.028015751000000002 | 0.10317952 | 0.009026687 | 0.018213745 | 0.03228745 | 0.07245033 | -0.01997892 | |||
| 16 | 15 | 420.0 | 0.0 | 2737.0 | 2737.0 | 79.0 | 2737.0 | 0.998336800000036 | 3.0 | 30.0 | 0.0 | 0.008781690090836491 | 0.00899884267405712 | 0.028885878622531887 | 0.00047134244232438505 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.04500962 | 0.024723325 | 0.10789993 | 0.017506445 | |||||||
| 17 | 16 | 441.0 | 0.0 | 2822.0 | 2822.0 | 85.0 | 2822.0 | 0.998252650000038 | 1.0 | 20.0 | 0.0 | 0.011111788584717685 | 0.00964176097294723 | 0.030850913375616074 | 0.0004762174794450402 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.050733815999999994 | 0.028628142999999998 | 0.12953582 | 0.018588755 | |||||||
| 18 | 17 | 497.0 | 0.0 | 3045.0 | 3045.0 | 223.0 | 3045.0 | 0.9980318800000428 | 2.0 | 30.0 | 0.0 | 0.00828668451010474 | 0.010699894323199828 | 0.04358338564634323 | 0.00020791786664631215 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.039435297 | 0.027343287999999997 | 0.12071342 | 0.007059440500000001 | 0.014257256999999999 | 0.019365441 | 0.04348784 | -0.0063439063 | |||
| 19 | 18 | 519.0 | 0.0 | 3133.0 | 3133.0 | 88.0 | 3133.0 | 0.9979447600000446 | 1.0 | 10.0 | 0.0 | 0.0074549241412155826 | 0.008195051001161512 | 0.028971081599593163 | 0.0003202491207048297 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.037259682999999995 | 0.021548636 | 0.073957734 | 0.01237885 | |||||||
| 20 | 19 | 586.0 | 0.0 | 3399.0 | 3399.0 | 266.0 | 3399.0 | 0.9976814200000504 | 1.0 | 15.0 | 0.0 | 0.006056426719257629 | 0.009519012818678223 | 0.043173693120479584 | 0.00011111447383882478 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.030213887000000002 | 0.025259253 | 0.11475632 | 0.005044707 | |||||||
| 21 | 20 | 644.0 | 0.0 | 3631.0 | 3631.0 | 232.0 | 3631.0 | 0.9974517400000552 | 3.0 | 30.0 | 0.0 | 0.007892606775416864 | 0.009331413396285886 | 0.02925945073366165 | 0.00020737151498906317 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.038149226 | 0.025099216 | 0.08682343 | 0.0064632813 | -0.0009132011300000001 | 0.012333746999999999 | 0.009670014499999999 | -0.025862066 | |||
| 22 | 21 | 691.0 | 0.0 | 3822.0 | 3822.0 | 191.0 | 3822.0 | 0.9972626500000594 | 1.0 | 5.0 | 0.0 | 0.0065839045484144074 | 0.010710195076304628 | 0.055450454354286194 | 0.00015095918206498027 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.03362562 | 0.03347708 | 0.17523270000000002 | 0.007759502 | 0.008254298 | 0.019461052 | 0.04853519 | -0.01426878 | |||
| 23 | 22 | 763.0 | 0.0 | 4107.0 | 4107.0 | 285.0 | 4107.0 | 0.9969805000000656 | 5.0 | 100.0 | 0.0 | 0.006797392681821495 | 0.009432101821733327 | 0.04118099808692932 | 0.00019709108164533973 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.03493503 | 0.025949332999999998 | 0.10501147 | 0.009826525 | 0.014940828 | 0.022241406000000002 | 0.05235735 | -0.00962076 | |||
| 24 | 23 | 842.0 | 0.0 | 4426.0 | 4426.0 | 319.0 | 4426.0 | 0.9966646900000724 | 7.0 | 90.0 | 0.0 | 0.006717705090096975 | 0.009711801205322595 | 0.05458200722932816 | 0.0001975365012185648 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.035762466 | 0.028132005 | 0.17399962 | 0.007998915 | |||||||
| 25 | 24 | 871.0 | 0.0 | 4540.0 | 4540.0 | 114.0 | 4540.0 | 0.9965518300000747 | 0.0 | 0.0 | 0.0 | 0.004121708562236343 | 0.006990884078555905 | 0.0262324009090662 | 0.00016586761921644208 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.02528197 | 0.022645405 | 0.08977601 | 0.0065642386 | 0.02154913 | 0.01743115 | 0.038836032 | -0.0025164383 | |||
| 26 | 25 | 908.0 | 0.0 | 4687.0 | 4687.0 | 147.0 | 4687.0 | 0.9964063000000779 | 2.0 | 45.0 | 0.0 | 0.005335816105110319 | 0.0065088615879247145 | 0.01545584015548229 | 0.00013705540914088488 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.030282034 | 0.02378779 | 0.06643725 | 0.0073994235 |