mirror of
https://github.com/gryf/coach.git
synced 2026-01-09 15:24:13 +01:00
6.3 KiB
6.3 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 | Discounted Return/Mean | Discounted Return/Stdev | Discounted Return/Max | Discounted Return/Min | Entropy/Mean | Entropy/Stdev | Entropy/Max | Entropy/Min | Q/Mean | Q/Stdev | Q/Max | Q/Min | Q Values/Mean | Q Values/Stdev | Q Values/Max | Q Values/Min | Value Loss/Mean | Value Loss/Stdev | Value Loss/Max | Value Loss/Min |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 1 | 0.0 | 1.0 | 486.0 | 1.0 | 486.0 | 486.0 | 0.5 | 0.0 | 1.027285241237078 | 0.8961037725396955 | 3.502959469093688 | 0.0 | |||||||||||||||||||||||||||||||||
| 3 | 2 | 0.0 | 1.0 | 87.0 | 1.0 | 87.0 | 573.0 | 0.5 | 0.0 | 0.2991949731169189 | 0.4147830569909918 | 1.0 | 0.0 | |||||||||||||||||||||||||||||||||
| 4 | 3 | 0.0 | 1.0 | 149.0 | 1.0 | 149.0 | 722.0 | 0.5 | 0.0 | 1.089942054123867 | 0.6773639260883686 | 1.9560606270183023 | 0.0 | |||||||||||||||||||||||||||||||||
| 5 | 4 | 0.0 | 1.0 | 335.0 | 1.0 | 335.0 | 1057.0 | 0.5 | 0.0 | 1.6150170189100268 | 1.2171006279541683 | 4.3034191502088746 | 0.0 | |||||||||||||||||||||||||||||||||
| 6 | 5 | 49.0 | 0.0 | 250.0 | 1.0 | 250.0 | 1307.0 | 0.4975499999999989 | 3.0 | 60.0 | 0.0 | 0.9619660716012052 | 0.5271840370028462 | 1.9877214348890249 | 0.0 | 0.06523297 | 0.039132793 | 0.16515993 | -0.04698263 | 0.03715847 | 0.16062164 | 0.9986223 | 5.2241390000000005e-06 | |||||||||||||||||||||||
| 7 | 6 | 105.0 | 0.0 | 278.0 | 1.0 | 278.0 | 1585.0 | 0.4948255999999978 | 2.0 | 25.0 | 0.0 | 0.6504435080212637 | 0.4990360198105554 | 1.877521022998968 | 0.0 | 0.06105925 | 0.028913812999999997 | 0.2251295 | 0.00031058473 | 0.025028551 | 0.12800282 | 0.8860348 | 4.704531e-05 | |||||||||||||||||||||||
| 8 | 7 | 215.0 | 0.0 | 547.0 | 1.0 | 547.0 | 2132.0 | 0.4894649999999954 | 9.0 | 70.0 | 0.0 | 1.1668219204868608 | 1.139774286228071 | 3.981172292031248 | 0.0 | 0.09291774 | 0.041909117 | 0.29434606 | 0.016387725 | 0.06240651 | 0.19966795 | 0.9046893 | 0.00021752282999999999 | |||||||||||||||||||||||
| 9 | 8 | 256.0 | 0.0 | 202.0 | 1.0 | 202.0 | 2334.0 | 0.4874853999999946 | 3.0 | 30.0 | 0.0 | 1.143254407638888 | 0.7651739473233898 | 2.6822034344079513 | 0.0 | 0.0812066 | 0.034699347 | 0.22075215 | 0.033963714 | 0.06826939 | 0.23026471 | 0.8968558000000001 | 5.273441e-06 | |||||||||||||||||||||||
| 10 | 9 | 271.0 | 0.0 | 76.0 | 1.0 | 76.0 | 2410.0 | 0.4867405999999943 | 2.0 | 45.0 | 0.0 | 0.6040699250474294 | 0.6770046574946313 | 1.8097278682212583 | 0.0 | 0.08223315 | 0.042012982000000004 | 0.20047347 | 0.0048412476 | 0.0409274 | 0.09979676 | 0.36558379999999996 | 0.0012286354 | |||||||||||||||||||||||
| 11 | 10 | 330.0 | 0.0 | 292.0 | 1.0 | 292.0 | 2702.0 | 0.483878999999993 | 2.0 | 35.0 | 0.0 | 0.5188424987401079 | 0.3205545284923169 | 1.1982742565889144 | 0.0 | 0.07179869 | 0.028891182999999997 | 0.1457309 | -0.0005440897 | 0.020115541 | 0.114067726 | 0.85806334 | 1.0554600499999999e-05 | |||||||||||||||||||||||
| 12 | 11 | 368.0 | 0.0 | 189.0 | 1.0 | 189.0 | 2891.0 | 0.4820267999999922 | 5.0 | 55.0 | 0.0 | 1.6514130362698112 | 1.0340472182590057 | 3.338928212866469 | 0.0 | 0.10357409 | 0.038070783 | 0.19072735 | 0.013136728 | 0.07165525 | 0.20934153 | 0.96637666 | 9.3623305e-05 | |||||||||||||||||||||||
| 13 | 12 | 385.0 | 0.0 | 85.0 | 1.0 | 85.0 | 2976.0 | 0.4811937999999918 | 2.0 | 55.0 | 0.0 | 0.6644740252476246 | 0.6445878033949242 | 1.7547192872036326 | 0.0 | 0.08559471 | 0.036382526 | 0.19190781 | 0.038743064 | 0.09200458 | 0.2459315 | 0.92060333 | 0.001493881 | |||||||||||||||||||||||
| 14 | 13 | 439.0 | 0.0 | 271.0 | 1.0 | 271.0 | 3247.0 | 0.4785379999999907 | 3.0 | 30.0 | 0.0 | 0.9805352211608988 | 0.7225009315821939 | 2.6900602158160227 | 0.0 | 0.07257719 | 0.036623262000000004 | 0.22449888 | 0.017026702 | 0.051612765 | 0.19161709 | 0.93902147 | 6.006258000000001e-05 | |||||||||||||||||||||||
| 15 | 14 | 489.0 | 0.0 | 247.0 | 1.0 | 247.0 | 3494.0 | 0.4761173999999896 | 3.0 | 30.0 | 0.0 | 0.7239330793237315 | 0.6866779551191587 | 2.2598491521703985 | 0.0 | 0.09624664 | 0.028458447999999997 | 0.18122105 | 0.04136644 | 0.04521184 | 0.17329727 | 0.93528235 | 0.00010959508 | |||||||||||||||||||||||
| 16 | 15 | 554.0 | 0.0 | 322.0 | 1.0 | 322.0 | 3816.0 | 0.4729617999999883 | 7.0 | 75.0 | 0.0 | 1.7027014745135145 | 0.8785415129990072 | 3.3646815869626545 | 0.0 | 0.08818049 | 0.03232697 | 0.19298476 | 0.01802668 | 0.06566782 | 0.20002598 | 0.93202585 | 0.000119806835 | |||||||||||||||||||||||
| 17 | 16 | 591.0 | 0.0 | 185.0 | 1.0 | 185.0 | 4001.0 | 0.4711487999999875 | 3.0 | 35.0 | 0.0 | 0.906880276626358 | 0.5305160768996153 | 1.8687458127689778 | 0.0 | 0.10646282 | 0.030883757 | 0.19681731 | 0.052096736 | 0.062161777 | 0.18977489 | 0.77037257 | 0.0006098728 | |||||||||||||||||||||||
| 18 | 17 | 628.0 | 0.0 | 186.0 | 1.0 | 186.0 | 4187.0 | 0.4693259999999867 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.10503617 | 0.02636908 | 0.17513691 | 0.058163125 | 0.0040708557 | 0.0018935091 | 0.008554585 | 0.0012393859 | |||||||||||||||||||||||
| 19 | 18 | 644.0 | 0.0 | 80.0 | 1.0 | 80.0 | 4267.0 | 0.4685419999999864 | 2.0 | 15.0 | 0.0 | 0.702410295740766 | 0.7598837978189577 | 1.886384871716129 | 0.0 | 0.088057734 | 0.014962838999999999 | 0.13839622 | 0.06381006 | 0.077688575 | 0.20810342 | 0.7685311 | 5.7868005e-05 | |||||||||||||||||||||||
| 20 | 19 | 663.0 | 0.0 | 93.0 | 1.0 | 93.0 | 4360.0 | 0.467630599999986 | 2.0 | 35.0 | 0.0 | 0.7877925962882179 | 0.6771086001101679 | 1.8016305895390456 | 0.0 | 0.07237811400000001 | 0.03177111 | 0.15346664 | 0.027509372999999997 | 0.07317008 | 0.22093417 | 0.92313504 | 0.00035924176 | |||||||||||||||||||||||
| 21 | 20 | 705.0 | 0.0 | 210.0 | 1.0 | 210.0 | 4570.0 | 0.465572599999985 | 3.0 | 30.0 | 0.0 | 1.1264211896676488 | 0.6963700234551127 | 2.5143201556468044 | 0.0 | 0.07745734 | 0.03569484 | 0.17048967 | -0.0018016198 | 0.033146697999999995 | 0.11387434 | 0.54282963 | 9.045503e-05 | |||||||||||||||||||||||
| 22 | 21 | 724.0 | 0.0 | 94.0 | 1.0 | 94.0 | 4664.0 | 0.4646513999999847 | 2.0 | 45.0 | 0.0 | 0.7487142977587385 | 0.6585762420290013 | 1.770043145805155 | 0.0 | 0.085581295 | 0.031317193 | 0.16033286 | 0.03945991 | 0.031889725 | 0.09107567 | 0.37029892 | 0.00048189453 | |||||||||||||||||||||||
| 23 | 22 | 846.0 | 0.0 | 608.0 | 1.0 | 608.0 | 5272.0 | 0.4586929999999821 | 12.0 | 340.0 | 0.0 | 1.7842522377946013 | 1.2596094953837684 | 4.9927930148931186 | 0.0 | 0.104008555 | 0.040039804 | 0.20478153 | 0.008027065 | 0.06521728 | 0.18897916 | 0.82046026 | 5.0944614e-05 | |||||||||||||||||||||||
| 24 | 23 | 885.0 | 0.0 | 194.0 | 1.0 | 194.0 | 5466.0 | 0.4567917999999813 | 6.0 | 80.0 | 0.0 | 2.0644794324027784 | 1.0634426104295631 | 3.98052088029283 | 0.0 | 0.119464405 | 0.034119558 | 0.18460895 | 0.039233252 | 0.06616199 | 0.16974789 | 0.8555218000000001 | 0.0008571786999999999 | |||||||||||||||||||||||
| 25 | 24 | 904.0 | 0.0 | 95.0 | 1.0 | 95.0 | 5561.0 | 0.4558607999999809 | 1.0 | 30.0 | 0.0 | 0.21724812248036252 | 0.3855022238888541 | 1.0 | 0.0 | 0.09762655 | 0.029675594 | 0.1733855 | 0.06255842 | 0.031556234 | 0.11838596 | 0.5196432 | 0.0013286468 | |||||||||||||||||||||||
| 26 | 25 | 923.0 | 0.0 | 94.0 | 1.0 | 94.0 | 5655.0 | 0.4549395999999805 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.06350739 | 0.014013496 | 0.10299649999999999 | 0.03182298 | 0.00033242480000000006 | 0.00019209432000000002 | 0.0007463536500000001 | 0.000114553884 |