mirror of
https://github.com/gryf/coach.git
synced 2026-01-04 04:44:15 +01:00
5.1 KiB
5.1 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 | 43.0 | 0.0 | 218.0 | 1.0 | 218.0 | 1275.0 | 0.4978635999999991 | 4.0 | 30.0 | 0.0 | 1.4355558153956027 | 0.8743774426398123 | 3.18289891640664 | 0.0 | 0.049821895 | 0.040794298 | 0.16144831 | -0.04194873599999999 | 0.06658878 | 0.20887113 | 0.92870796 | 1.3539827000000001e-05 | |||||||||||||||||||||||
| 7 | 6 | 82.0 | 0.0 | 195.0 | 1.0 | 195.0 | 1470.0 | 0.4959525999999982 | 2.0 | 35.0 | 0.0 | 0.5266968407467524 | 0.3693588813641733 | 1.2762516676992082 | 0.0 | 0.07430909599999999 | 0.031378473999999996 | 0.15561001 | 0.017140895 | 0.03804031 | 0.16481854 | 0.9850528000000001 | 0.0002183407 | |||||||||||||||||||||||
| 8 | 7 | 131.0 | 0.0 | 243.0 | 1.0 | 243.0 | 1713.0 | 0.4935711999999972 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.04265518 | 0.020237265 | 0.12036709 | -0.012695962 | 0.0005867248999999999 | 0.00071001943 | 0.004012562 | 5.224298e-06 | |||||||||||||||||||||||
| 9 | 8 | 183.0 | 0.0 | 260.0 | 1.0 | 260.0 | 1973.0 | 0.4910231999999961 | 6.0 | 45.0 | 0.0 | 1.8445302223733409 | 0.9773846948142106 | 3.529722201807415 | 0.0 | 0.065202 | 0.0400596 | 0.21712853 | 0.0068587554 | 0.065516554 | 0.19554858 | 0.8884774999999999 | 3.5797817e-05 | |||||||||||||||||||||||
| 10 | 9 | 249.0 | 0.0 | 329.0 | 1.0 | 329.0 | 2302.0 | 0.4877989999999947 | 6.0 | 100.0 | 0.0 | 1.392666868216866 | 1.0394071747173437 | 3.6111183571713448 | 0.0 | 0.056425206 | 0.037720352 | 0.16072667 | -0.04126611 | 0.036703362999999996 | 0.11380449 | 0.5483772 | 0.00036559267999999997 | |||||||||||||||||||||||
| 11 | 10 | 355.0 | 0.0 | 529.0 | 1.0 | 529.0 | 2831.0 | 0.4826147999999925 | 4.0 | 55.0 | 0.0 | 0.7058811552247987 | 0.6338784621102189 | 2.6758599618307444 | 0.0 | 0.0295469 | 0.019959169 | 0.100820765 | -0.019850466 | 0.026555283 | 0.14218670000000003 | 0.95402884 | 3.3959244e-05 | |||||||||||||||||||||||
| 12 | 11 | 382.0 | 0.0 | 136.0 | 1.0 | 136.0 | 2967.0 | 0.4812819999999919 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.070838 | 0.020381957 | 0.12719424 | 0.027900666 | 0.0011888286999999999 | 0.0012110863 | 0.005692898 | 2.8870036e-05 | |||||||||||||||||||||||
| 13 | 12 | 437.0 | 0.0 | 272.0 | 1.0 | 272.0 | 3239.0 | 0.4786163999999907 | 5.0 | 75.0 | 0.0 | 0.7965494499155914 | 0.7676873795288424 | 3.0706061095113872 | 0.0 | 0.06791638 | 0.030165499999999998 | 0.14470898 | -0.03135575 | 0.055119842 | 0.17865935 | 0.89836913 | 0.00041550235 | |||||||||||||||||||||||
| 14 | 13 | 526.0 | 0.0 | 445.0 | 1.0 | 445.0 | 3684.0 | 0.4742553999999888 | 6.0 | 70.0 | 0.0 | 0.9250639900550434 | 1.3791755980793503 | 4.6070750958301225 | 0.0 | 0.05033615599999999 | 0.04090539 | 0.21611296 | -0.00539122 | 0.04374561 | 0.15804026 | 0.88217527 | 5.6085350000000005e-06 | |||||||||||||||||||||||
| 15 | 14 | 568.0 | 0.0 | 211.0 | 1.0 | 211.0 | 3895.0 | 0.472187599999988 | 4.0 | 35.0 | 0.0 | 1.3211683635631786 | 0.6688764763247202 | 2.6041154043144044 | 0.0 | 0.06951321 | 0.026168478999999998 | 0.1383483 | 0.017367069 | 0.037633757999999996 | 0.12640582 | 0.7049002 | 7.566997400000001e-05 | |||||||||||||||||||||||
| 16 | 15 | 588.0 | 0.0 | 99.0 | 1.0 | 99.0 | 3994.0 | 0.4712173999999875 | 1.0 | 20.0 | 0.0 | 0.3275464150906228 | 0.4105264429665964 | 1.0 | 0.0 | 0.061873578 | 0.027288637999999997 | 0.11769849 | 0.006314104 | 0.039941784 | 0.16420019 | 0.7365783 | 0.0004206792 | |||||||||||||||||||||||
| 17 | 16 | 628.0 | 0.0 | 197.0 | 1.0 | 197.0 | 4191.0 | 0.4692867999999867 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.035919555 | 0.019500284 | 0.095511 | -0.011271331 | 0.0005676733 | 0.00042882026 | 0.0016585776 | 2.5987260999999998e-05 | |||||||||||||||||||||||
| 18 | 17 | 737.0 | 0.0 | 543.0 | 1.0 | 543.0 | 4734.0 | 0.4639653999999844 | 13.0 | 230.0 | 0.0 | 2.12068282338126 | 1.613926274284711 | 4.811923111070045 | 0.0 | 0.07359602 | 0.031097147999999998 | 0.16789229 | -0.0072538974 | 0.055959634 | 0.15358616 | 0.7472243000000001 | 1.1038916999999998e-05 | |||||||||||||||||||||||
| 19 | 18 | 770.0 | 0.0 | 163.0 | 1.0 | 163.0 | 4897.0 | 0.4623679999999837 | 1.0 | 20.0 | 0.0 | 0.3999428745445137 | 0.3331373421595941 | 1.0 | 0.0 | 0.039978374 | 0.023399489 | 0.09573812 | -0.004045846 | 0.030746099 | 0.16456035 | 0.9469624 | 0.00016566872 | |||||||||||||||||||||||
| 20 | 19 | 813.0 | 0.0 | 216.0 | 1.0 | 216.0 | 5113.0 | 0.4602511999999828 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.041446723 | 0.015750267 | 0.08521996 | 0.0036349134 | 0.0005720068599999999 | 0.0005356747 | 0.0020601498 | 6.6438793e-06 | |||||||||||||||||||||||
| 21 | 20 | 855.0 | 0.0 | 207.0 | 1.0 | 207.0 | 5320.0 | 0.4582225999999819 | 3.0 | 30.0 | 0.0 | 1.1196867985922996 | 0.7253527014570459 | 2.5969380989884208 | 0.0 | 0.07086054 | 0.030868992 | 0.15472650000000002 | 0.021865197000000003 | 0.045209922 | 0.16471039 | 0.9026728999999999 | 7.0652815e-05 |