mirror of
https://github.com/gryf/coach.git
synced 2026-02-17 23:05:51 +01:00
2.5 KiB
2.5 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 | 478.0 | 478.0 | 478.0 | 478.0 | 1.0 | 0.0 | |||||||||||||||||||||
| 3 | 2 | 0.0 | 1.0 | 956.0 | 956.0 | 478.0 | 956.0 | 1.0 | 0.0 | |||||||||||||||||||||
| 4 | 3 | 0.0 | 1.0 | 1434.0 | 1434.0 | 478.0 | 1434.0 | 1.0 | 0.0 | |||||||||||||||||||||
| 5 | 4 | 120.0 | 0.0 | 1912.0 | 1912.0 | 478.0 | 1912.0 | 0.9995698000000142 | 9.0 | 9.0 | 0.0 | 0.009663151060431118 | 0.013676663237646413 | 0.060224123299121864 | 4.512001760303974e-05 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.06051638 | 0.042551804000000006 | 0.22626723 | 0.0057771252 | |||||||
| 6 | 5 | 239.0 | 0.0 | 2390.0 | 2390.0 | 478.0 | 2390.0 | 0.9991396000000284 | 14.0 | 14.0 | 0.0 | 0.010185969424235415 | 0.01273001908156945 | 0.05133835971355438 | 0.0001901108626043424 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.071132325 | 0.042716417 | 0.23749977 | 0.014687435 | |||||||
| 7 | 6 | 359.0 | 0.0 | 2868.0 | 2868.0 | 478.0 | 2868.0 | 0.9987094000000424 | 5.0 | 5.0 | 0.0 | 0.009524562051471246 | 0.009567511935832385 | 0.036678917706012726 | 0.00025706662563607097 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.076720946 | 0.039715942000000004 | 0.18440181 | 0.012763031999999999 | |||||||
| 8 | 7 | 478.0 | 0.0 | 3346.0 | 3346.0 | 478.0 | 3346.0 | 0.9982792000000568 | 7.0 | 7.0 | 0.0 | 0.008778206794962929 | 0.01083872213612712 | 0.05636880546808243 | 6.587376992683858e-05 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.07076845 | 0.041428506000000004 | 0.20715882 | 0.006995787 | |||||||
| 9 | 8 | 598.0 | 0.0 | 3824.0 | 3824.0 | 478.0 | 3824.0 | 0.9978490000000708 | 9.0 | 9.0 | 0.0 | 0.009846380206727191 | 0.013011878941093766 | 0.06951349228620529 | 0.00021574157290160656 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.077692814 | 0.045143295 | 0.22578509 | 0.013560652 | |||||||
| 10 | 9 | 717.0 | 0.0 | 4302.0 | 4302.0 | 478.0 | 4302.0 | 0.997418800000085 | 5.0 | 5.0 | 0.0 | 0.007978798927589584 | 0.008021061916904503 | 0.029912894591689113 | 0.0002371315349591896 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.07165227 | 0.037239626 | 0.16855638 | 0.012386461000000001 | 0.043533697999999996 | 0.021518622999999997 | 0.08633506 | -0.007646310999999999 | |||
| 11 | 10 | 837.0 | 0.0 | 4780.0 | 4780.0 | 478.0 | 4780.0 | 0.9969886000000991 | 7.0 | 7.0 | 0.0 | 0.006560324567666006 | 0.009694367656889826 | 0.0584893636405468 | 0.00016549747670069337 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.062156662 | 0.042624008 | 0.20502545 | 0.010010223 |