Upload training_log.json with huggingface_hub
Browse files- training_log.json +3870 -0
training_log.json
CHANGED
|
@@ -592,5 +592,3875 @@
|
|
| 592 |
"mean_length": 3142.3,
|
| 593 |
"loss": 1779.034423828125,
|
| 594 |
"sps": 167.8109154720703
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 595 |
}
|
| 596 |
]
|
|
|
|
| 592 |
"mean_length": 3142.3,
|
| 593 |
"loss": 1779.034423828125,
|
| 594 |
"sps": 167.8109154720703
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"update": 335,
|
| 598 |
+
"global_step": 1372160,
|
| 599 |
+
"num_episodes": 378,
|
| 600 |
+
"mean_reward": 357.36821466445923,
|
| 601 |
+
"mean_length": 2510.76,
|
| 602 |
+
"loss": 33.58185958862305,
|
| 603 |
+
"sps": 451.94218989282257
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"update": 340,
|
| 607 |
+
"global_step": 1392640,
|
| 608 |
+
"num_episodes": 388,
|
| 609 |
+
"mean_reward": 455.7884948730469,
|
| 610 |
+
"mean_length": 2739.63,
|
| 611 |
+
"loss": 16.64685821533203,
|
| 612 |
+
"sps": 273.0263210661101
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"update": 345,
|
| 616 |
+
"global_step": 1413120,
|
| 617 |
+
"num_episodes": 390,
|
| 618 |
+
"mean_reward": 456.36600038528445,
|
| 619 |
+
"mean_length": 2831.63,
|
| 620 |
+
"loss": 53.800376892089844,
|
| 621 |
+
"sps": 262.8572795282316
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"update": 350,
|
| 625 |
+
"global_step": 1433600,
|
| 626 |
+
"num_episodes": 392,
|
| 627 |
+
"mean_reward": 358.3022264003754,
|
| 628 |
+
"mean_length": 2855.26,
|
| 629 |
+
"loss": 275.63385009765625,
|
| 630 |
+
"sps": 446.63750460322206
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"update": 355,
|
| 634 |
+
"global_step": 1454080,
|
| 635 |
+
"num_episodes": 407,
|
| 636 |
+
"mean_reward": 375.7198329591751,
|
| 637 |
+
"mean_length": 2911.33,
|
| 638 |
+
"loss": 8.481382369995117,
|
| 639 |
+
"sps": 367.7815116282032
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"update": 360,
|
| 643 |
+
"global_step": 1474560,
|
| 644 |
+
"num_episodes": 417,
|
| 645 |
+
"mean_reward": 297.66134167194366,
|
| 646 |
+
"mean_length": 2867.69,
|
| 647 |
+
"loss": 23.24544334411621,
|
| 648 |
+
"sps": 538.1701556626739
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"update": 365,
|
| 652 |
+
"global_step": 1495040,
|
| 653 |
+
"num_episodes": 423,
|
| 654 |
+
"mean_reward": 297.34756595134735,
|
| 655 |
+
"mean_length": 2864.35,
|
| 656 |
+
"loss": 4.300067901611328,
|
| 657 |
+
"sps": 967.5617761077667
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"update": 370,
|
| 661 |
+
"global_step": 1515520,
|
| 662 |
+
"num_episodes": 426,
|
| 663 |
+
"mean_reward": 420.4760777759552,
|
| 664 |
+
"mean_length": 2769.38,
|
| 665 |
+
"loss": 0.5866292715072632,
|
| 666 |
+
"sps": 666.1817947182782
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"update": 375,
|
| 670 |
+
"global_step": 1536000,
|
| 671 |
+
"num_episodes": 429,
|
| 672 |
+
"mean_reward": 420.90687354564665,
|
| 673 |
+
"mean_length": 2720.24,
|
| 674 |
+
"loss": 1.5303698778152466,
|
| 675 |
+
"sps": 387.94660115994657
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"update": 380,
|
| 679 |
+
"global_step": 1556480,
|
| 680 |
+
"num_episodes": 447,
|
| 681 |
+
"mean_reward": 356.93565448284147,
|
| 682 |
+
"mean_length": 2600.92,
|
| 683 |
+
"loss": 1.487197995185852,
|
| 684 |
+
"sps": 563.1387661188227
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"update": 385,
|
| 688 |
+
"global_step": 1576960,
|
| 689 |
+
"num_episodes": 452,
|
| 690 |
+
"mean_reward": 357.39739652633665,
|
| 691 |
+
"mean_length": 2840.12,
|
| 692 |
+
"loss": 139.934326171875,
|
| 693 |
+
"sps": 419.07382914990956
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"update": 390,
|
| 697 |
+
"global_step": 1597440,
|
| 698 |
+
"num_episodes": 456,
|
| 699 |
+
"mean_reward": 320.4454140949249,
|
| 700 |
+
"mean_length": 2739.7,
|
| 701 |
+
"loss": 35.25250244140625,
|
| 702 |
+
"sps": 1220.6982535284524
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"update": 395,
|
| 706 |
+
"global_step": 1617920,
|
| 707 |
+
"num_episodes": 456,
|
| 708 |
+
"mean_reward": 320.4454140949249,
|
| 709 |
+
"mean_length": 2739.7,
|
| 710 |
+
"loss": 3.3828349113464355,
|
| 711 |
+
"sps": 1342.5750178490377
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"update": 400,
|
| 715 |
+
"global_step": 1638400,
|
| 716 |
+
"num_episodes": 464,
|
| 717 |
+
"mean_reward": 328.27054366588595,
|
| 718 |
+
"mean_length": 2746.2,
|
| 719 |
+
"loss": 9.8130521774292,
|
| 720 |
+
"sps": 1796.7926258567122
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"update": 405,
|
| 724 |
+
"global_step": 1658880,
|
| 725 |
+
"num_episodes": 470,
|
| 726 |
+
"mean_reward": 469.22999305725097,
|
| 727 |
+
"mean_length": 2992.85,
|
| 728 |
+
"loss": 1.3559972047805786,
|
| 729 |
+
"sps": 692.6458346671639
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"update": 410,
|
| 733 |
+
"global_step": 1679360,
|
| 734 |
+
"num_episodes": 490,
|
| 735 |
+
"mean_reward": 372.7216357469559,
|
| 736 |
+
"mean_length": 2776.16,
|
| 737 |
+
"loss": 1.9204107522964478,
|
| 738 |
+
"sps": 654.3363015594651
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"update": 415,
|
| 742 |
+
"global_step": 1699840,
|
| 743 |
+
"num_episodes": 498,
|
| 744 |
+
"mean_reward": 355.0806073760986,
|
| 745 |
+
"mean_length": 2364.43,
|
| 746 |
+
"loss": 0.20851367712020874,
|
| 747 |
+
"sps": 1574.1015970289384
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"update": 420,
|
| 751 |
+
"global_step": 1720320,
|
| 752 |
+
"num_episodes": 505,
|
| 753 |
+
"mean_reward": 357.1250058794022,
|
| 754 |
+
"mean_length": 2659.22,
|
| 755 |
+
"loss": 0.8760831356048584,
|
| 756 |
+
"sps": 725.5072374754453
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"update": 425,
|
| 760 |
+
"global_step": 1740800,
|
| 761 |
+
"num_episodes": 519,
|
| 762 |
+
"mean_reward": 338.12661921024323,
|
| 763 |
+
"mean_length": 2572.09,
|
| 764 |
+
"loss": 0.7201396822929382,
|
| 765 |
+
"sps": 774.136034580983
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"update": 430,
|
| 769 |
+
"global_step": 1761280,
|
| 770 |
+
"num_episodes": 520,
|
| 771 |
+
"mean_reward": 338.7818141031265,
|
| 772 |
+
"mean_length": 2670.69,
|
| 773 |
+
"loss": 0.2984998822212219,
|
| 774 |
+
"sps": 593.9586130082629
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"update": 435,
|
| 778 |
+
"global_step": 1781760,
|
| 779 |
+
"num_episodes": 524,
|
| 780 |
+
"mean_reward": 200.51355738162994,
|
| 781 |
+
"mean_length": 2677.33,
|
| 782 |
+
"loss": 0.6558288931846619,
|
| 783 |
+
"sps": 563.7237889903446
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"update": 440,
|
| 787 |
+
"global_step": 1802240,
|
| 788 |
+
"num_episodes": 531,
|
| 789 |
+
"mean_reward": 195.75862418174745,
|
| 790 |
+
"mean_length": 2684.96,
|
| 791 |
+
"loss": 0.6485836505889893,
|
| 792 |
+
"sps": 801.5054039510692
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"update": 445,
|
| 796 |
+
"global_step": 1822720,
|
| 797 |
+
"num_episodes": 541,
|
| 798 |
+
"mean_reward": 182.37921036720275,
|
| 799 |
+
"mean_length": 2787.68,
|
| 800 |
+
"loss": 0.9738303422927856,
|
| 801 |
+
"sps": 552.0177086572941
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"update": 450,
|
| 805 |
+
"global_step": 1843200,
|
| 806 |
+
"num_episodes": 544,
|
| 807 |
+
"mean_reward": 182.38307575702666,
|
| 808 |
+
"mean_length": 2886.96,
|
| 809 |
+
"loss": 0.35677605867385864,
|
| 810 |
+
"sps": 1078.6474451651457
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"update": 455,
|
| 814 |
+
"global_step": 1863680,
|
| 815 |
+
"num_episodes": 545,
|
| 816 |
+
"mean_reward": 183.31554008960723,
|
| 817 |
+
"mean_length": 2983.98,
|
| 818 |
+
"loss": 2.5785653591156006,
|
| 819 |
+
"sps": 2238.2674979327135
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"update": 460,
|
| 823 |
+
"global_step": 1884160,
|
| 824 |
+
"num_episodes": 552,
|
| 825 |
+
"mean_reward": 184.02062775611878,
|
| 826 |
+
"mean_length": 2848.2,
|
| 827 |
+
"loss": 2.8595657348632812,
|
| 828 |
+
"sps": 788.1771239252804
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"update": 465,
|
| 832 |
+
"global_step": 1904640,
|
| 833 |
+
"num_episodes": 556,
|
| 834 |
+
"mean_reward": 185.80799278259278,
|
| 835 |
+
"mean_length": 3043.7,
|
| 836 |
+
"loss": 1.9609827995300293,
|
| 837 |
+
"sps": 577.1914698783215
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"update": 470,
|
| 841 |
+
"global_step": 1925120,
|
| 842 |
+
"num_episodes": 562,
|
| 843 |
+
"mean_reward": 187.01453431129457,
|
| 844 |
+
"mean_length": 3143.24,
|
| 845 |
+
"loss": 3.339183807373047,
|
| 846 |
+
"sps": 1007.594504286708
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"update": 475,
|
| 850 |
+
"global_step": 1945600,
|
| 851 |
+
"num_episodes": 566,
|
| 852 |
+
"mean_reward": 173.54088757038116,
|
| 853 |
+
"mean_length": 2963.92,
|
| 854 |
+
"loss": 0.6618616580963135,
|
| 855 |
+
"sps": 901.0594653949358
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"update": 480,
|
| 859 |
+
"global_step": 1966080,
|
| 860 |
+
"num_episodes": 575,
|
| 861 |
+
"mean_reward": 33.9250515460968,
|
| 862 |
+
"mean_length": 2871.77,
|
| 863 |
+
"loss": 2.1673176288604736,
|
| 864 |
+
"sps": 637.9211744730668
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"update": 485,
|
| 868 |
+
"global_step": 1986560,
|
| 869 |
+
"num_episodes": 586,
|
| 870 |
+
"mean_reward": 34.479522528648374,
|
| 871 |
+
"mean_length": 3064.33,
|
| 872 |
+
"loss": 0.5433505773544312,
|
| 873 |
+
"sps": 434.7028394813384
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"update": 490,
|
| 877 |
+
"global_step": 2007040,
|
| 878 |
+
"num_episodes": 596,
|
| 879 |
+
"mean_reward": 35.79800989627838,
|
| 880 |
+
"mean_length": 3282.82,
|
| 881 |
+
"loss": 0.78948974609375,
|
| 882 |
+
"sps": 336.9612684589691
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"update": 495,
|
| 886 |
+
"global_step": 2027520,
|
| 887 |
+
"num_episodes": 604,
|
| 888 |
+
"mean_reward": 33.232103657722476,
|
| 889 |
+
"mean_length": 2993.3,
|
| 890 |
+
"loss": 1.0133846998214722,
|
| 891 |
+
"sps": 825.0153267212829
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"update": 500,
|
| 895 |
+
"global_step": 2048000,
|
| 896 |
+
"num_episodes": 608,
|
| 897 |
+
"mean_reward": 35.19134169101715,
|
| 898 |
+
"mean_length": 3091.99,
|
| 899 |
+
"loss": 2.315326690673828,
|
| 900 |
+
"sps": 1734.6708087716852
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"update": 505,
|
| 904 |
+
"global_step": 2068480,
|
| 905 |
+
"num_episodes": 626,
|
| 906 |
+
"mean_reward": 34.19606147289276,
|
| 907 |
+
"mean_length": 2992.5,
|
| 908 |
+
"loss": 0.5885242223739624,
|
| 909 |
+
"sps": 326.9154194294925
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"update": 510,
|
| 913 |
+
"global_step": 2088960,
|
| 914 |
+
"num_episodes": 635,
|
| 915 |
+
"mean_reward": 34.653258776664735,
|
| 916 |
+
"mean_length": 2903.6,
|
| 917 |
+
"loss": 0.5012519359588623,
|
| 918 |
+
"sps": 618.1195825840496
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"update": 515,
|
| 922 |
+
"global_step": 2109440,
|
| 923 |
+
"num_episodes": 648,
|
| 924 |
+
"mean_reward": 31.289368829727174,
|
| 925 |
+
"mean_length": 2418.77,
|
| 926 |
+
"loss": 3.98177433013916,
|
| 927 |
+
"sps": 646.2346813472644
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"update": 520,
|
| 931 |
+
"global_step": 2129920,
|
| 932 |
+
"num_episodes": 655,
|
| 933 |
+
"mean_reward": 31.192284369468688,
|
| 934 |
+
"mean_length": 2226.18,
|
| 935 |
+
"loss": 0.6265271306037903,
|
| 936 |
+
"sps": 1099.3023206141552
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"update": 525,
|
| 940 |
+
"global_step": 2150400,
|
| 941 |
+
"num_episodes": 660,
|
| 942 |
+
"mean_reward": 31.34406463623047,
|
| 943 |
+
"mean_length": 2219.04,
|
| 944 |
+
"loss": 0.10834737122058868,
|
| 945 |
+
"sps": 1013.9364910908357
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"update": 530,
|
| 949 |
+
"global_step": 2170880,
|
| 950 |
+
"num_episodes": 663,
|
| 951 |
+
"mean_reward": 32.43585729598999,
|
| 952 |
+
"mean_length": 2310.25,
|
| 953 |
+
"loss": 0.16828738152980804,
|
| 954 |
+
"sps": 2044.258556649656
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"update": 535,
|
| 958 |
+
"global_step": 2191360,
|
| 959 |
+
"num_episodes": 673,
|
| 960 |
+
"mean_reward": 31.12276816368103,
|
| 961 |
+
"mean_length": 2188.44,
|
| 962 |
+
"loss": 0.30583497881889343,
|
| 963 |
+
"sps": 669.970940042682
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"update": 540,
|
| 967 |
+
"global_step": 2211840,
|
| 968 |
+
"num_episodes": 688,
|
| 969 |
+
"mean_reward": 31.249693727493288,
|
| 970 |
+
"mean_length": 2081.05,
|
| 971 |
+
"loss": 0.17176635563373566,
|
| 972 |
+
"sps": 590.5779813457752
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"update": 545,
|
| 976 |
+
"global_step": 2232320,
|
| 977 |
+
"num_episodes": 694,
|
| 978 |
+
"mean_reward": 33.27913472175598,
|
| 979 |
+
"mean_length": 2258.75,
|
| 980 |
+
"loss": 0.7694998979568481,
|
| 981 |
+
"sps": 738.4276136206116
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"update": 550,
|
| 985 |
+
"global_step": 2252800,
|
| 986 |
+
"num_episodes": 698,
|
| 987 |
+
"mean_reward": 33.9422331905365,
|
| 988 |
+
"mean_length": 2351.64,
|
| 989 |
+
"loss": 0.15182125568389893,
|
| 990 |
+
"sps": 762.723220730318
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"update": 555,
|
| 994 |
+
"global_step": 2273280,
|
| 995 |
+
"num_episodes": 700,
|
| 996 |
+
"mean_reward": 34.04119193077087,
|
| 997 |
+
"mean_length": 2350.76,
|
| 998 |
+
"loss": 0.032472074031829834,
|
| 999 |
+
"sps": 1245.5515732240913
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"update": 560,
|
| 1003 |
+
"global_step": 2293760,
|
| 1004 |
+
"num_episodes": 712,
|
| 1005 |
+
"mean_reward": 32.31116131782532,
|
| 1006 |
+
"mean_length": 2355.04,
|
| 1007 |
+
"loss": 0.5084341168403625,
|
| 1008 |
+
"sps": 356.9310128125497
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"update": 565,
|
| 1012 |
+
"global_step": 2314240,
|
| 1013 |
+
"num_episodes": 719,
|
| 1014 |
+
"mean_reward": 32.47976410865784,
|
| 1015 |
+
"mean_length": 2441.54,
|
| 1016 |
+
"loss": 0.21268926560878754,
|
| 1017 |
+
"sps": 649.2244348171059
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"update": 570,
|
| 1021 |
+
"global_step": 2334720,
|
| 1022 |
+
"num_episodes": 728,
|
| 1023 |
+
"mean_reward": 33.27659282684326,
|
| 1024 |
+
"mean_length": 2530.94,
|
| 1025 |
+
"loss": 0.9577451348304749,
|
| 1026 |
+
"sps": 768.1072804561215
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"update": 575,
|
| 1030 |
+
"global_step": 2355200,
|
| 1031 |
+
"num_episodes": 734,
|
| 1032 |
+
"mean_reward": 31.69405174255371,
|
| 1033 |
+
"mean_length": 2412.76,
|
| 1034 |
+
"loss": 1.0152896642684937,
|
| 1035 |
+
"sps": 1202.6180581266553
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"update": 580,
|
| 1039 |
+
"global_step": 2375680,
|
| 1040 |
+
"num_episodes": 751,
|
| 1041 |
+
"mean_reward": 32.80648866415024,
|
| 1042 |
+
"mean_length": 2678.86,
|
| 1043 |
+
"loss": 1.551302433013916,
|
| 1044 |
+
"sps": 620.7046830826843
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"update": 585,
|
| 1048 |
+
"global_step": 2396160,
|
| 1049 |
+
"num_episodes": 757,
|
| 1050 |
+
"mean_reward": 29.564244215488433,
|
| 1051 |
+
"mean_length": 2585.36,
|
| 1052 |
+
"loss": 3.1353652477264404,
|
| 1053 |
+
"sps": 488.49247923421996
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"update": 590,
|
| 1057 |
+
"global_step": 2416640,
|
| 1058 |
+
"num_episodes": 758,
|
| 1059 |
+
"mean_reward": 30.12968365430832,
|
| 1060 |
+
"mean_length": 2685.11,
|
| 1061 |
+
"loss": 1.9931682348251343,
|
| 1062 |
+
"sps": 1344.82690419507
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"update": 595,
|
| 1066 |
+
"global_step": 2437120,
|
| 1067 |
+
"num_episodes": 765,
|
| 1068 |
+
"mean_reward": 28.753595340251923,
|
| 1069 |
+
"mean_length": 2505.15,
|
| 1070 |
+
"loss": 1.9217519760131836,
|
| 1071 |
+
"sps": 447.9409443511792
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"update": 600,
|
| 1075 |
+
"global_step": 2457600,
|
| 1076 |
+
"num_episodes": 777,
|
| 1077 |
+
"mean_reward": 30.216613895893097,
|
| 1078 |
+
"mean_length": 2711.46,
|
| 1079 |
+
"loss": 18.632978439331055,
|
| 1080 |
+
"sps": 404.03595919196334
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"update": 605,
|
| 1084 |
+
"global_step": 2478080,
|
| 1085 |
+
"num_episodes": 795,
|
| 1086 |
+
"mean_reward": 25.763007862567903,
|
| 1087 |
+
"mean_length": 2472.96,
|
| 1088 |
+
"loss": 0.08484360575675964,
|
| 1089 |
+
"sps": 273.80019869630905
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"update": 610,
|
| 1093 |
+
"global_step": 2498560,
|
| 1094 |
+
"num_episodes": 800,
|
| 1095 |
+
"mean_reward": 25.233678991794587,
|
| 1096 |
+
"mean_length": 2472.55,
|
| 1097 |
+
"loss": 1.4983996152877808,
|
| 1098 |
+
"sps": 842.5169450671826
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"update": 615,
|
| 1102 |
+
"global_step": 2519040,
|
| 1103 |
+
"num_episodes": 800,
|
| 1104 |
+
"mean_reward": 25.233678991794587,
|
| 1105 |
+
"mean_length": 2472.55,
|
| 1106 |
+
"loss": 2.3043322563171387,
|
| 1107 |
+
"sps": 1633.9246020797414
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"update": 620,
|
| 1111 |
+
"global_step": 2539520,
|
| 1112 |
+
"num_episodes": 810,
|
| 1113 |
+
"mean_reward": 25.826587975025177,
|
| 1114 |
+
"mean_length": 2510.48,
|
| 1115 |
+
"loss": 0.21852731704711914,
|
| 1116 |
+
"sps": 518.4307357532686
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"update": 625,
|
| 1120 |
+
"global_step": 2560000,
|
| 1121 |
+
"num_episodes": 814,
|
| 1122 |
+
"mean_reward": 25.645928237438202,
|
| 1123 |
+
"mean_length": 2512.63,
|
| 1124 |
+
"loss": 1.0583765506744385,
|
| 1125 |
+
"sps": 581.0047205132955
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"update": 630,
|
| 1129 |
+
"global_step": 2580480,
|
| 1130 |
+
"num_episodes": 823,
|
| 1131 |
+
"mean_reward": 25.49915248632431,
|
| 1132 |
+
"mean_length": 2527.36,
|
| 1133 |
+
"loss": 1.795029878616333,
|
| 1134 |
+
"sps": 537.504310438823
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"update": 635,
|
| 1138 |
+
"global_step": 2600960,
|
| 1139 |
+
"num_episodes": 825,
|
| 1140 |
+
"mean_reward": 26.937079560756683,
|
| 1141 |
+
"mean_length": 2620.74,
|
| 1142 |
+
"loss": 0.2923164963722229,
|
| 1143 |
+
"sps": 1350.1934205312384
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"update": 640,
|
| 1147 |
+
"global_step": 2621440,
|
| 1148 |
+
"num_episodes": 834,
|
| 1149 |
+
"mean_reward": 29.924575612545013,
|
| 1150 |
+
"mean_length": 2905.58,
|
| 1151 |
+
"loss": 0.43789708614349365,
|
| 1152 |
+
"sps": 280.4967413720513
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"update": 645,
|
| 1156 |
+
"global_step": 2641920,
|
| 1157 |
+
"num_episodes": 836,
|
| 1158 |
+
"mean_reward": 28.948164422512054,
|
| 1159 |
+
"mean_length": 2820.95,
|
| 1160 |
+
"loss": 1.5149576663970947,
|
| 1161 |
+
"sps": 640.5808040483822
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"update": 650,
|
| 1165 |
+
"global_step": 2662400,
|
| 1166 |
+
"num_episodes": 843,
|
| 1167 |
+
"mean_reward": 35.76819623708725,
|
| 1168 |
+
"mean_length": 3020.26,
|
| 1169 |
+
"loss": 1.5319448709487915,
|
| 1170 |
+
"sps": 573.556787061315
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"update": 655,
|
| 1174 |
+
"global_step": 2682880,
|
| 1175 |
+
"num_episodes": 851,
|
| 1176 |
+
"mean_reward": 35.12200962543488,
|
| 1177 |
+
"mean_length": 2929.69,
|
| 1178 |
+
"loss": 0.4334838390350342,
|
| 1179 |
+
"sps": 721.898659363473
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"update": 660,
|
| 1183 |
+
"global_step": 2703360,
|
| 1184 |
+
"num_episodes": 863,
|
| 1185 |
+
"mean_reward": 34.17141466140747,
|
| 1186 |
+
"mean_length": 2837.57,
|
| 1187 |
+
"loss": 15.400986671447754,
|
| 1188 |
+
"sps": 531.226152703821
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"update": 665,
|
| 1192 |
+
"global_step": 2723840,
|
| 1193 |
+
"num_episodes": 871,
|
| 1194 |
+
"mean_reward": 34.406737427711484,
|
| 1195 |
+
"mean_length": 2847.12,
|
| 1196 |
+
"loss": -0.022274762392044067,
|
| 1197 |
+
"sps": 1102.2418013565505
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"update": 670,
|
| 1201 |
+
"global_step": 2744320,
|
| 1202 |
+
"num_episodes": 880,
|
| 1203 |
+
"mean_reward": 33.42318947315216,
|
| 1204 |
+
"mean_length": 2744.42,
|
| 1205 |
+
"loss": 0.21278248727321625,
|
| 1206 |
+
"sps": 932.5471353242045
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"update": 675,
|
| 1210 |
+
"global_step": 2764800,
|
| 1211 |
+
"num_episodes": 881,
|
| 1212 |
+
"mean_reward": 35.02722130298614,
|
| 1213 |
+
"mean_length": 2793.45,
|
| 1214 |
+
"loss": 0.48318442702293396,
|
| 1215 |
+
"sps": 849.2902333548969
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"update": 680,
|
| 1219 |
+
"global_step": 2785280,
|
| 1220 |
+
"num_episodes": 894,
|
| 1221 |
+
"mean_reward": 42.5996656703949,
|
| 1222 |
+
"mean_length": 2993.97,
|
| 1223 |
+
"loss": 0.9185795187950134,
|
| 1224 |
+
"sps": 476.82647813725623
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"update": 685,
|
| 1228 |
+
"global_step": 2805760,
|
| 1229 |
+
"num_episodes": 914,
|
| 1230 |
+
"mean_reward": 40.827002143859865,
|
| 1231 |
+
"mean_length": 2561.69,
|
| 1232 |
+
"loss": 1.2765486240386963,
|
| 1233 |
+
"sps": 255.71578525021312
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"update": 690,
|
| 1237 |
+
"global_step": 2826240,
|
| 1238 |
+
"num_episodes": 925,
|
| 1239 |
+
"mean_reward": 45.62547200202942,
|
| 1240 |
+
"mean_length": 2469.27,
|
| 1241 |
+
"loss": 2.3010942935943604,
|
| 1242 |
+
"sps": 570.2368795975491
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"update": 695,
|
| 1246 |
+
"global_step": 2846720,
|
| 1247 |
+
"num_episodes": 931,
|
| 1248 |
+
"mean_reward": 43.9872697687149,
|
| 1249 |
+
"mean_length": 2287.32,
|
| 1250 |
+
"loss": 1.1779371500015259,
|
| 1251 |
+
"sps": 532.4176047731756
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"update": 700,
|
| 1255 |
+
"global_step": 2867200,
|
| 1256 |
+
"num_episodes": 943,
|
| 1257 |
+
"mean_reward": 36.38923056125641,
|
| 1258 |
+
"mean_length": 1897.85,
|
| 1259 |
+
"loss": 0.6398267149925232,
|
| 1260 |
+
"sps": 501.06106420522286
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"update": 705,
|
| 1264 |
+
"global_step": 2887680,
|
| 1265 |
+
"num_episodes": 952,
|
| 1266 |
+
"mean_reward": 38.85928546905517,
|
| 1267 |
+
"mean_length": 2189.91,
|
| 1268 |
+
"loss": 0.7464686632156372,
|
| 1269 |
+
"sps": 358.482733937848
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"update": 710,
|
| 1273 |
+
"global_step": 2908160,
|
| 1274 |
+
"num_episodes": 960,
|
| 1275 |
+
"mean_reward": 38.50984364032745,
|
| 1276 |
+
"mean_length": 2181.81,
|
| 1277 |
+
"loss": 0.819063663482666,
|
| 1278 |
+
"sps": 729.0695475685854
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"update": 715,
|
| 1282 |
+
"global_step": 2928640,
|
| 1283 |
+
"num_episodes": 960,
|
| 1284 |
+
"mean_reward": 38.50984364032745,
|
| 1285 |
+
"mean_length": 2181.81,
|
| 1286 |
+
"loss": 1.3829450607299805,
|
| 1287 |
+
"sps": 2103.44152639025
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"update": 720,
|
| 1291 |
+
"global_step": 2949120,
|
| 1292 |
+
"num_episodes": 961,
|
| 1293 |
+
"mean_reward": 38.30655426502228,
|
| 1294 |
+
"mean_length": 2181.81,
|
| 1295 |
+
"loss": 1.3242486715316772,
|
| 1296 |
+
"sps": 2180.924028748301
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"update": 725,
|
| 1300 |
+
"global_step": 2969600,
|
| 1301 |
+
"num_episodes": 979,
|
| 1302 |
+
"mean_reward": 37.64626069068909,
|
| 1303 |
+
"mean_length": 2258.86,
|
| 1304 |
+
"loss": 0.6890235543251038,
|
| 1305 |
+
"sps": 512.7806225711571
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"update": 730,
|
| 1309 |
+
"global_step": 2990080,
|
| 1310 |
+
"num_episodes": 993,
|
| 1311 |
+
"mean_reward": 29.446645002365113,
|
| 1312 |
+
"mean_length": 2178.52,
|
| 1313 |
+
"loss": 1.424858570098877,
|
| 1314 |
+
"sps": 397.19464657996275
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"update": 735,
|
| 1318 |
+
"global_step": 3010560,
|
| 1319 |
+
"num_episodes": 994,
|
| 1320 |
+
"mean_reward": 29.469437551498412,
|
| 1321 |
+
"mean_length": 2182.57,
|
| 1322 |
+
"loss": 1.9823501110076904,
|
| 1323 |
+
"sps": 742.698176618862
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"update": 740,
|
| 1327 |
+
"global_step": 3031040,
|
| 1328 |
+
"num_episodes": 995,
|
| 1329 |
+
"mean_reward": 29.75782982826233,
|
| 1330 |
+
"mean_length": 2282.33,
|
| 1331 |
+
"loss": 0.30816513299942017,
|
| 1332 |
+
"sps": 1825.6853767545124
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"update": 745,
|
| 1336 |
+
"global_step": 3051520,
|
| 1337 |
+
"num_episodes": 998,
|
| 1338 |
+
"mean_reward": 30.453793020248412,
|
| 1339 |
+
"mean_length": 2473.99,
|
| 1340 |
+
"loss": 3.092510938644409,
|
| 1341 |
+
"sps": 1555.5380368163708
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"update": 750,
|
| 1345 |
+
"global_step": 3072000,
|
| 1346 |
+
"num_episodes": 1010,
|
| 1347 |
+
"mean_reward": 31.862056040763854,
|
| 1348 |
+
"mean_length": 2872.71,
|
| 1349 |
+
"loss": 3.4220612049102783,
|
| 1350 |
+
"sps": 266.50791667174065
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"update": 755,
|
| 1354 |
+
"global_step": 3092480,
|
| 1355 |
+
"num_episodes": 1019,
|
| 1356 |
+
"mean_reward": 28.9614812707901,
|
| 1357 |
+
"mean_length": 2699.59,
|
| 1358 |
+
"loss": 1.2745823860168457,
|
| 1359 |
+
"sps": 753.5067688712668
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"update": 760,
|
| 1363 |
+
"global_step": 3112960,
|
| 1364 |
+
"num_episodes": 1020,
|
| 1365 |
+
"mean_reward": 23.99162916660309,
|
| 1366 |
+
"mean_length": 2699.59,
|
| 1367 |
+
"loss": 0.8926928043365479,
|
| 1368 |
+
"sps": 1444.3258733361963
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"update": 765,
|
| 1372 |
+
"global_step": 3133440,
|
| 1373 |
+
"num_episodes": 1024,
|
| 1374 |
+
"mean_reward": 30.025504064559936,
|
| 1375 |
+
"mean_length": 2889.38,
|
| 1376 |
+
"loss": 1.112790822982788,
|
| 1377 |
+
"sps": 756.883715254125
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"update": 770,
|
| 1381 |
+
"global_step": 3153920,
|
| 1382 |
+
"num_episodes": 1034,
|
| 1383 |
+
"mean_reward": 36.13991012096405,
|
| 1384 |
+
"mean_length": 3187.15,
|
| 1385 |
+
"loss": 0.43345746397972107,
|
| 1386 |
+
"sps": 419.40821109391015
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"update": 775,
|
| 1390 |
+
"global_step": 3174400,
|
| 1391 |
+
"num_episodes": 1050,
|
| 1392 |
+
"mean_reward": 32.24160755157471,
|
| 1393 |
+
"mean_length": 2985.91,
|
| 1394 |
+
"loss": 0.13569332659244537,
|
| 1395 |
+
"sps": 317.4046328348688
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"update": 780,
|
| 1399 |
+
"global_step": 3194880,
|
| 1400 |
+
"num_episodes": 1061,
|
| 1401 |
+
"mean_reward": 30.67223885536194,
|
| 1402 |
+
"mean_length": 2711.19,
|
| 1403 |
+
"loss": 0.2064545899629593,
|
| 1404 |
+
"sps": 303.1813456850613
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"update": 785,
|
| 1408 |
+
"global_step": 3215360,
|
| 1409 |
+
"num_episodes": 1072,
|
| 1410 |
+
"mean_reward": 29.705427560806275,
|
| 1411 |
+
"mean_length": 2524.86,
|
| 1412 |
+
"loss": 4.488283634185791,
|
| 1413 |
+
"sps": 913.592632749929
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"update": 790,
|
| 1417 |
+
"global_step": 3235840,
|
| 1418 |
+
"num_episodes": 1085,
|
| 1419 |
+
"mean_reward": 32.955479860305786,
|
| 1420 |
+
"mean_length": 2618.62,
|
| 1421 |
+
"loss": 0.05505555868148804,
|
| 1422 |
+
"sps": 607.269974208857
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"update": 795,
|
| 1426 |
+
"global_step": 3256320,
|
| 1427 |
+
"num_episodes": 1097,
|
| 1428 |
+
"mean_reward": 31.909876976013184,
|
| 1429 |
+
"mean_length": 2214.73,
|
| 1430 |
+
"loss": 1.9556808471679688,
|
| 1431 |
+
"sps": 747.2261381867389
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"update": 800,
|
| 1435 |
+
"global_step": 3276800,
|
| 1436 |
+
"num_episodes": 1106,
|
| 1437 |
+
"mean_reward": 29.67423951148987,
|
| 1438 |
+
"mean_length": 1915.87,
|
| 1439 |
+
"loss": 2.1206791400909424,
|
| 1440 |
+
"sps": 701.3988516159834
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"update": 805,
|
| 1444 |
+
"global_step": 3297280,
|
| 1445 |
+
"num_episodes": 1110,
|
| 1446 |
+
"mean_reward": 30.086654043197633,
|
| 1447 |
+
"mean_length": 2005.75,
|
| 1448 |
+
"loss": 0.5833985805511475,
|
| 1449 |
+
"sps": 660.5544733393301
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"update": 810,
|
| 1453 |
+
"global_step": 3317760,
|
| 1454 |
+
"num_episodes": 1115,
|
| 1455 |
+
"mean_reward": 32.238635430336,
|
| 1456 |
+
"mean_length": 2171.27,
|
| 1457 |
+
"loss": 0.4146590232849121,
|
| 1458 |
+
"sps": 1094.4092641494085
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"update": 815,
|
| 1462 |
+
"global_step": 3338240,
|
| 1463 |
+
"num_episodes": 1120,
|
| 1464 |
+
"mean_reward": 33.369399318695066,
|
| 1465 |
+
"mean_length": 2262.48,
|
| 1466 |
+
"loss": 2.585177183151245,
|
| 1467 |
+
"sps": 901.8559204378539
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"update": 820,
|
| 1471 |
+
"global_step": 3358720,
|
| 1472 |
+
"num_episodes": 1130,
|
| 1473 |
+
"mean_reward": 27.537890434265137,
|
| 1474 |
+
"mean_length": 2050.2,
|
| 1475 |
+
"loss": 0.5106171369552612,
|
| 1476 |
+
"sps": 838.9275291477041
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"update": 825,
|
| 1480 |
+
"global_step": 3379200,
|
| 1481 |
+
"num_episodes": 1136,
|
| 1482 |
+
"mean_reward": 23.029513311386108,
|
| 1483 |
+
"mean_length": 2161.34,
|
| 1484 |
+
"loss": 4.071342468261719,
|
| 1485 |
+
"sps": 1617.4028966230667
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"update": 830,
|
| 1489 |
+
"global_step": 3399680,
|
| 1490 |
+
"num_episodes": 1138,
|
| 1491 |
+
"mean_reward": 23.361328144073486,
|
| 1492 |
+
"mean_length": 2259.74,
|
| 1493 |
+
"loss": 0.30649739503860474,
|
| 1494 |
+
"sps": 489.67958732294835
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"update": 835,
|
| 1498 |
+
"global_step": 3420160,
|
| 1499 |
+
"num_episodes": 1146,
|
| 1500 |
+
"mean_reward": 29.256564235687257,
|
| 1501 |
+
"mean_length": 2379.17,
|
| 1502 |
+
"loss": 0.2716136574745178,
|
| 1503 |
+
"sps": 789.1092351378779
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"update": 840,
|
| 1507 |
+
"global_step": 3440640,
|
| 1508 |
+
"num_episodes": 1152,
|
| 1509 |
+
"mean_reward": 30.681161608695984,
|
| 1510 |
+
"mean_length": 2564.53,
|
| 1511 |
+
"loss": 3.510643720626831,
|
| 1512 |
+
"sps": 465.91684356996774
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"update": 845,
|
| 1516 |
+
"global_step": 3461120,
|
| 1517 |
+
"num_episodes": 1157,
|
| 1518 |
+
"mean_reward": 31.814847540855407,
|
| 1519 |
+
"mean_length": 2661.46,
|
| 1520 |
+
"loss": 0.2368174046278,
|
| 1521 |
+
"sps": 970.5356676833453
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"update": 850,
|
| 1525 |
+
"global_step": 3481600,
|
| 1526 |
+
"num_episodes": 1158,
|
| 1527 |
+
"mean_reward": 32.19375528335571,
|
| 1528 |
+
"mean_length": 2760.37,
|
| 1529 |
+
"loss": 1.0439393520355225,
|
| 1530 |
+
"sps": 2118.0253570743016
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"update": 855,
|
| 1534 |
+
"global_step": 3502080,
|
| 1535 |
+
"num_episodes": 1167,
|
| 1536 |
+
"mean_reward": 32.78835594654083,
|
| 1537 |
+
"mean_length": 2934.75,
|
| 1538 |
+
"loss": 0.11038707196712494,
|
| 1539 |
+
"sps": 373.62636209376416
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"update": 860,
|
| 1543 |
+
"global_step": 3522560,
|
| 1544 |
+
"num_episodes": 1171,
|
| 1545 |
+
"mean_reward": 38.54492960453033,
|
| 1546 |
+
"mean_length": 3055.33,
|
| 1547 |
+
"loss": 0.27012330293655396,
|
| 1548 |
+
"sps": 811.5381951612115
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"update": 865,
|
| 1552 |
+
"global_step": 3543040,
|
| 1553 |
+
"num_episodes": 1182,
|
| 1554 |
+
"mean_reward": 38.79421305179596,
|
| 1555 |
+
"mean_length": 3135.05,
|
| 1556 |
+
"loss": 0.8694961071014404,
|
| 1557 |
+
"sps": 643.9358039841488
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"update": 870,
|
| 1561 |
+
"global_step": 3563520,
|
| 1562 |
+
"num_episodes": 1187,
|
| 1563 |
+
"mean_reward": 37.14653766155243,
|
| 1564 |
+
"mean_length": 3053.45,
|
| 1565 |
+
"loss": 1.2393195629119873,
|
| 1566 |
+
"sps": 871.9844580529647
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"update": 875,
|
| 1570 |
+
"global_step": 3584000,
|
| 1571 |
+
"num_episodes": 1194,
|
| 1572 |
+
"mean_reward": 40.78861089706421,
|
| 1573 |
+
"mean_length": 3345.54,
|
| 1574 |
+
"loss": 0.6096416115760803,
|
| 1575 |
+
"sps": 304.93330977862365
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"update": 880,
|
| 1579 |
+
"global_step": 3604480,
|
| 1580 |
+
"num_episodes": 1201,
|
| 1581 |
+
"mean_reward": 39.81052246570587,
|
| 1582 |
+
"mean_length": 3252.28,
|
| 1583 |
+
"loss": 0.6608580946922302,
|
| 1584 |
+
"sps": 677.495925390962
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"update": 885,
|
| 1588 |
+
"global_step": 3624960,
|
| 1589 |
+
"num_episodes": 1215,
|
| 1590 |
+
"mean_reward": 38.70529013156891,
|
| 1591 |
+
"mean_length": 3165.08,
|
| 1592 |
+
"loss": 1.2741384506225586,
|
| 1593 |
+
"sps": 854.5639976310788
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"update": 890,
|
| 1597 |
+
"global_step": 3645440,
|
| 1598 |
+
"num_episodes": 1215,
|
| 1599 |
+
"mean_reward": 38.70529013156891,
|
| 1600 |
+
"mean_length": 3165.08,
|
| 1601 |
+
"loss": 0.5457536578178406,
|
| 1602 |
+
"sps": 1511.837849491964
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"update": 895,
|
| 1606 |
+
"global_step": 3665920,
|
| 1607 |
+
"num_episodes": 1220,
|
| 1608 |
+
"mean_reward": 39.244035544395445,
|
| 1609 |
+
"mean_length": 3264.42,
|
| 1610 |
+
"loss": 0.6924870014190674,
|
| 1611 |
+
"sps": 556.2715786447075
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"update": 900,
|
| 1615 |
+
"global_step": 3686400,
|
| 1616 |
+
"num_episodes": 1232,
|
| 1617 |
+
"mean_reward": 46.50887234210968,
|
| 1618 |
+
"mean_length": 3173.4,
|
| 1619 |
+
"loss": 1.7522594928741455,
|
| 1620 |
+
"sps": 699.9425408800316
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"update": 905,
|
| 1624 |
+
"global_step": 3706880,
|
| 1625 |
+
"num_episodes": 1245,
|
| 1626 |
+
"mean_reward": 41.68342576980591,
|
| 1627 |
+
"mean_length": 2950.87,
|
| 1628 |
+
"loss": 1.1043925285339355,
|
| 1629 |
+
"sps": 375.42107758469984
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"update": 910,
|
| 1633 |
+
"global_step": 3727360,
|
| 1634 |
+
"num_episodes": 1257,
|
| 1635 |
+
"mean_reward": 38.028645734786984,
|
| 1636 |
+
"mean_length": 2550.61,
|
| 1637 |
+
"loss": 0.11873626708984375,
|
| 1638 |
+
"sps": 856.8550488972196
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"update": 915,
|
| 1642 |
+
"global_step": 3747840,
|
| 1643 |
+
"num_episodes": 1265,
|
| 1644 |
+
"mean_reward": 38.954245281219485,
|
| 1645 |
+
"mean_length": 2549.56,
|
| 1646 |
+
"loss": 0.31198206543922424,
|
| 1647 |
+
"sps": 690.3971885269259
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"update": 920,
|
| 1651 |
+
"global_step": 3768320,
|
| 1652 |
+
"num_episodes": 1269,
|
| 1653 |
+
"mean_reward": 34.42387727260589,
|
| 1654 |
+
"mean_length": 2518.34,
|
| 1655 |
+
"loss": 1.7575799226760864,
|
| 1656 |
+
"sps": 1152.958968508612
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"update": 925,
|
| 1660 |
+
"global_step": 3788800,
|
| 1661 |
+
"num_episodes": 1274,
|
| 1662 |
+
"mean_reward": 34.58799042224884,
|
| 1663 |
+
"mean_length": 2520.98,
|
| 1664 |
+
"loss": 0.3646126985549927,
|
| 1665 |
+
"sps": 1100.5795244909316
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"update": 930,
|
| 1669 |
+
"global_step": 3809280,
|
| 1670 |
+
"num_episodes": 1276,
|
| 1671 |
+
"mean_reward": 36.83985797405243,
|
| 1672 |
+
"mean_length": 2620.63,
|
| 1673 |
+
"loss": 0.5593718886375427,
|
| 1674 |
+
"sps": 999.9135216052517
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"update": 935,
|
| 1678 |
+
"global_step": 3829760,
|
| 1679 |
+
"num_episodes": 1292,
|
| 1680 |
+
"mean_reward": 36.57479173660278,
|
| 1681 |
+
"mean_length": 2520.6,
|
| 1682 |
+
"loss": 0.009059503674507141,
|
| 1683 |
+
"sps": 1097.323441932561
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"update": 940,
|
| 1687 |
+
"global_step": 3850240,
|
| 1688 |
+
"num_episodes": 1297,
|
| 1689 |
+
"mean_reward": 37.501826615333556,
|
| 1690 |
+
"mean_length": 2614.74,
|
| 1691 |
+
"loss": 0.686941385269165,
|
| 1692 |
+
"sps": 1048.1224362748299
|
| 1693 |
+
},
|
| 1694 |
+
{
|
| 1695 |
+
"update": 945,
|
| 1696 |
+
"global_step": 3870720,
|
| 1697 |
+
"num_episodes": 1302,
|
| 1698 |
+
"mean_reward": 38.2632510137558,
|
| 1699 |
+
"mean_length": 2706.87,
|
| 1700 |
+
"loss": 1.56045663356781,
|
| 1701 |
+
"sps": 984.6772159375175
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"update": 950,
|
| 1705 |
+
"global_step": 3891200,
|
| 1706 |
+
"num_episodes": 1303,
|
| 1707 |
+
"mean_reward": 37.39876995563507,
|
| 1708 |
+
"mean_length": 2611.05,
|
| 1709 |
+
"loss": 1.817370891571045,
|
| 1710 |
+
"sps": 662.4908033005096
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"update": 955,
|
| 1714 |
+
"global_step": 3911680,
|
| 1715 |
+
"num_episodes": 1312,
|
| 1716 |
+
"mean_reward": 38.347609777450565,
|
| 1717 |
+
"mean_length": 2799.94,
|
| 1718 |
+
"loss": 1.7936173677444458,
|
| 1719 |
+
"sps": 498.5900701113524
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"update": 960,
|
| 1723 |
+
"global_step": 3932160,
|
| 1724 |
+
"num_episodes": 1319,
|
| 1725 |
+
"mean_reward": 38.531728854179384,
|
| 1726 |
+
"mean_length": 2800.38,
|
| 1727 |
+
"loss": 0.8617715835571289,
|
| 1728 |
+
"sps": 288.6257663929259
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"update": 965,
|
| 1732 |
+
"global_step": 3952640,
|
| 1733 |
+
"num_episodes": 1325,
|
| 1734 |
+
"mean_reward": 32.38980568408966,
|
| 1735 |
+
"mean_length": 2706.94,
|
| 1736 |
+
"loss": 0.410921573638916,
|
| 1737 |
+
"sps": 729.5250188646075
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"update": 970,
|
| 1741 |
+
"global_step": 3973120,
|
| 1742 |
+
"num_episodes": 1330,
|
| 1743 |
+
"mean_reward": 33.02072194576263,
|
| 1744 |
+
"mean_length": 2800.87,
|
| 1745 |
+
"loss": 0.6215076446533203,
|
| 1746 |
+
"sps": 913.5447323136685
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"update": 975,
|
| 1750 |
+
"global_step": 3993600,
|
| 1751 |
+
"num_episodes": 1333,
|
| 1752 |
+
"mean_reward": 34.48237750530243,
|
| 1753 |
+
"mean_length": 2899.46,
|
| 1754 |
+
"loss": 1.4754104614257812,
|
| 1755 |
+
"sps": 857.6512350171981
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"update": 980,
|
| 1759 |
+
"global_step": 4014080,
|
| 1760 |
+
"num_episodes": 1346,
|
| 1761 |
+
"mean_reward": 35.15436544418335,
|
| 1762 |
+
"mean_length": 3006.69,
|
| 1763 |
+
"loss": 1.3220990896224976,
|
| 1764 |
+
"sps": 275.0666378661058
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"update": 985,
|
| 1768 |
+
"global_step": 4034560,
|
| 1769 |
+
"num_episodes": 1359,
|
| 1770 |
+
"mean_reward": 36.966177105903625,
|
| 1771 |
+
"mean_length": 3140.04,
|
| 1772 |
+
"loss": 0.31860384345054626,
|
| 1773 |
+
"sps": 723.735690218882
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"update": 990,
|
| 1777 |
+
"global_step": 4055040,
|
| 1778 |
+
"num_episodes": 1368,
|
| 1779 |
+
"mean_reward": 36.728344497680666,
|
| 1780 |
+
"mean_length": 2959.73,
|
| 1781 |
+
"loss": 5.1887078285217285,
|
| 1782 |
+
"sps": 773.332744431613
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"update": 995,
|
| 1786 |
+
"global_step": 4075520,
|
| 1787 |
+
"num_episodes": 1369,
|
| 1788 |
+
"mean_reward": 35.78023895263672,
|
| 1789 |
+
"mean_length": 2959.73,
|
| 1790 |
+
"loss": 1.6374891996383667,
|
| 1791 |
+
"sps": 2350.737845032927
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"update": 1000,
|
| 1795 |
+
"global_step": 4096000,
|
| 1796 |
+
"num_episodes": 1370,
|
| 1797 |
+
"mean_reward": 35.719558029174806,
|
| 1798 |
+
"mean_length": 2959.73,
|
| 1799 |
+
"loss": 1.2606910467147827,
|
| 1800 |
+
"sps": 2287.2771680470537
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"update": 1005,
|
| 1804 |
+
"global_step": 4116480,
|
| 1805 |
+
"num_episodes": 1381,
|
| 1806 |
+
"mean_reward": 37.67828846931457,
|
| 1807 |
+
"mean_length": 2963.83,
|
| 1808 |
+
"loss": 0.20636317133903503,
|
| 1809 |
+
"sps": 1606.0294791853535
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"update": 1010,
|
| 1813 |
+
"global_step": 4136960,
|
| 1814 |
+
"num_episodes": 1391,
|
| 1815 |
+
"mean_reward": 39.33717452049255,
|
| 1816 |
+
"mean_length": 3249.05,
|
| 1817 |
+
"loss": 3.9951727390289307,
|
| 1818 |
+
"sps": 418.63976772772594
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"update": 1015,
|
| 1822 |
+
"global_step": 4157440,
|
| 1823 |
+
"num_episodes": 1399,
|
| 1824 |
+
"mean_reward": 36.405463542938236,
|
| 1825 |
+
"mean_length": 2962.77,
|
| 1826 |
+
"loss": 1.837266445159912,
|
| 1827 |
+
"sps": 683.5481201646958
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"update": 1020,
|
| 1831 |
+
"global_step": 4177920,
|
| 1832 |
+
"num_episodes": 1401,
|
| 1833 |
+
"mean_reward": 35.86304131507873,
|
| 1834 |
+
"mean_length": 2879.03,
|
| 1835 |
+
"loss": 2.9102792739868164,
|
| 1836 |
+
"sps": 1089.8691629385837
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"update": 1025,
|
| 1840 |
+
"global_step": 4198400,
|
| 1841 |
+
"num_episodes": 1416,
|
| 1842 |
+
"mean_reward": 34.70472603797913,
|
| 1843 |
+
"mean_length": 2801.68,
|
| 1844 |
+
"loss": 0.9925887584686279,
|
| 1845 |
+
"sps": 255.81352094643265
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"update": 1030,
|
| 1849 |
+
"global_step": 4218880,
|
| 1850 |
+
"num_episodes": 1425,
|
| 1851 |
+
"mean_reward": 33.617551488876344,
|
| 1852 |
+
"mean_length": 2725.68,
|
| 1853 |
+
"loss": 1.9214203357696533,
|
| 1854 |
+
"sps": 737.2169737476238
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"update": 1035,
|
| 1858 |
+
"global_step": 4239360,
|
| 1859 |
+
"num_episodes": 1434,
|
| 1860 |
+
"mean_reward": 34.879857649803164,
|
| 1861 |
+
"mean_length": 2533.35,
|
| 1862 |
+
"loss": 0.2052566111087799,
|
| 1863 |
+
"sps": 579.7787814604097
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"update": 1040,
|
| 1867 |
+
"global_step": 4259840,
|
| 1868 |
+
"num_episodes": 1434,
|
| 1869 |
+
"mean_reward": 34.879857649803164,
|
| 1870 |
+
"mean_length": 2533.35,
|
| 1871 |
+
"loss": 1.6612746715545654,
|
| 1872 |
+
"sps": 1248.33251762393
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"update": 1045,
|
| 1876 |
+
"global_step": 4280320,
|
| 1877 |
+
"num_episodes": 1445,
|
| 1878 |
+
"mean_reward": 39.72180326938629,
|
| 1879 |
+
"mean_length": 2610.11,
|
| 1880 |
+
"loss": 4.8466691970825195,
|
| 1881 |
+
"sps": 656.9837380754918
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"update": 1050,
|
| 1885 |
+
"global_step": 4300800,
|
| 1886 |
+
"num_episodes": 1450,
|
| 1887 |
+
"mean_reward": 42.0785810136795,
|
| 1888 |
+
"mean_length": 2811.63,
|
| 1889 |
+
"loss": 2.377190351486206,
|
| 1890 |
+
"sps": 683.0332370956824
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"update": 1055,
|
| 1894 |
+
"global_step": 4321280,
|
| 1895 |
+
"num_episodes": 1461,
|
| 1896 |
+
"mean_reward": 39.593364839553836,
|
| 1897 |
+
"mean_length": 2808.07,
|
| 1898 |
+
"loss": 0.6159077882766724,
|
| 1899 |
+
"sps": 526.5738589213908
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"update": 1060,
|
| 1903 |
+
"global_step": 4341760,
|
| 1904 |
+
"num_episodes": 1461,
|
| 1905 |
+
"mean_reward": 39.593364839553836,
|
| 1906 |
+
"mean_length": 2808.07,
|
| 1907 |
+
"loss": 0.8465878963470459,
|
| 1908 |
+
"sps": 2184.9711988588206
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"update": 1065,
|
| 1912 |
+
"global_step": 4362240,
|
| 1913 |
+
"num_episodes": 1468,
|
| 1914 |
+
"mean_reward": 41.406082754135134,
|
| 1915 |
+
"mean_length": 2993.5,
|
| 1916 |
+
"loss": 2.0758755207061768,
|
| 1917 |
+
"sps": 756.2821057624998
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"update": 1070,
|
| 1921 |
+
"global_step": 4382720,
|
| 1922 |
+
"num_episodes": 1475,
|
| 1923 |
+
"mean_reward": 35.40320841789246,
|
| 1924 |
+
"mean_length": 2801.81,
|
| 1925 |
+
"loss": 9.254124641418457,
|
| 1926 |
+
"sps": 1308.8266389540704
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"update": 1075,
|
| 1930 |
+
"global_step": 4403200,
|
| 1931 |
+
"num_episodes": 1485,
|
| 1932 |
+
"mean_reward": 40.63698256492615,
|
| 1933 |
+
"mean_length": 2897.46,
|
| 1934 |
+
"loss": 0.5495067834854126,
|
| 1935 |
+
"sps": 799.4087672915922
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"update": 1080,
|
| 1939 |
+
"global_step": 4423680,
|
| 1940 |
+
"num_episodes": 1485,
|
| 1941 |
+
"mean_reward": 40.63698256492615,
|
| 1942 |
+
"mean_length": 2897.46,
|
| 1943 |
+
"loss": 0.5127925872802734,
|
| 1944 |
+
"sps": 1340.6154629856217
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"update": 1085,
|
| 1948 |
+
"global_step": 4444160,
|
| 1949 |
+
"num_episodes": 1486,
|
| 1950 |
+
"mean_reward": 41.25436541080475,
|
| 1951 |
+
"mean_length": 2996.57,
|
| 1952 |
+
"loss": 0.2694500684738159,
|
| 1953 |
+
"sps": 1837.4922707085245
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"update": 1090,
|
| 1957 |
+
"global_step": 4464640,
|
| 1958 |
+
"num_episodes": 1495,
|
| 1959 |
+
"mean_reward": 46.52874216079712,
|
| 1960 |
+
"mean_length": 3122.1,
|
| 1961 |
+
"loss": 10.304019927978516,
|
| 1962 |
+
"sps": 1046.1438942302716
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"update": 1095,
|
| 1966 |
+
"global_step": 4485120,
|
| 1967 |
+
"num_episodes": 1509,
|
| 1968 |
+
"mean_reward": 47.41412097454071,
|
| 1969 |
+
"mean_length": 3088.91,
|
| 1970 |
+
"loss": 4.403233051300049,
|
| 1971 |
+
"sps": 705.1397561929946
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"update": 1100,
|
| 1975 |
+
"global_step": 4505600,
|
| 1976 |
+
"num_episodes": 1509,
|
| 1977 |
+
"mean_reward": 47.41412097454071,
|
| 1978 |
+
"mean_length": 3088.91,
|
| 1979 |
+
"loss": 5.204225540161133,
|
| 1980 |
+
"sps": 956.5984516573334
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"update": 1105,
|
| 1984 |
+
"global_step": 4526080,
|
| 1985 |
+
"num_episodes": 1514,
|
| 1986 |
+
"mean_reward": 46.740014991760255,
|
| 1987 |
+
"mean_length": 3048.45,
|
| 1988 |
+
"loss": 1.3485753536224365,
|
| 1989 |
+
"sps": 2885.439969795025
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"update": 1110,
|
| 1993 |
+
"global_step": 4546560,
|
| 1994 |
+
"num_episodes": 1520,
|
| 1995 |
+
"mean_reward": 55.2595415019989,
|
| 1996 |
+
"mean_length": 3313.8,
|
| 1997 |
+
"loss": 2.248853921890259,
|
| 1998 |
+
"sps": 307.51773062645026
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"update": 1115,
|
| 2002 |
+
"global_step": 4567040,
|
| 2003 |
+
"num_episodes": 1535,
|
| 2004 |
+
"mean_reward": 45.75344041824341,
|
| 2005 |
+
"mean_length": 3241.81,
|
| 2006 |
+
"loss": 1.3050477504730225,
|
| 2007 |
+
"sps": 349.05706197896666
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"update": 1120,
|
| 2011 |
+
"global_step": 4587520,
|
| 2012 |
+
"num_episodes": 1538,
|
| 2013 |
+
"mean_reward": 48.896285104751584,
|
| 2014 |
+
"mean_length": 3154.78,
|
| 2015 |
+
"loss": 1.0057706832885742,
|
| 2016 |
+
"sps": 741.8276433683515
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"update": 1125,
|
| 2020 |
+
"global_step": 4608000,
|
| 2021 |
+
"num_episodes": 1543,
|
| 2022 |
+
"mean_reward": 49.45138314723968,
|
| 2023 |
+
"mean_length": 3312.76,
|
| 2024 |
+
"loss": 3.0420098304748535,
|
| 2025 |
+
"sps": 267.5648126417643
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"update": 1130,
|
| 2029 |
+
"global_step": 4628480,
|
| 2030 |
+
"num_episodes": 1554,
|
| 2031 |
+
"mean_reward": 45.64340697288513,
|
| 2032 |
+
"mean_length": 2967.91,
|
| 2033 |
+
"loss": 0.534530758857727,
|
| 2034 |
+
"sps": 595.2909007117904
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"update": 1135,
|
| 2038 |
+
"global_step": 4648960,
|
| 2039 |
+
"num_episodes": 1566,
|
| 2040 |
+
"mean_reward": 46.33692901611328,
|
| 2041 |
+
"mean_length": 3175.93,
|
| 2042 |
+
"loss": 12.374032974243164,
|
| 2043 |
+
"sps": 273.2022330683734
|
| 2044 |
+
},
|
| 2045 |
+
{
|
| 2046 |
+
"update": 1140,
|
| 2047 |
+
"global_step": 4669440,
|
| 2048 |
+
"num_episodes": 1574,
|
| 2049 |
+
"mean_reward": 45.48817714929581,
|
| 2050 |
+
"mean_length": 3007.35,
|
| 2051 |
+
"loss": 9.789308547973633,
|
| 2052 |
+
"sps": 468.42362264683504
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"update": 1145,
|
| 2056 |
+
"global_step": 4689920,
|
| 2057 |
+
"num_episodes": 1579,
|
| 2058 |
+
"mean_reward": 39.85454882383347,
|
| 2059 |
+
"mean_length": 2862.76,
|
| 2060 |
+
"loss": 14.043472290039062,
|
| 2061 |
+
"sps": 685.1921972366682
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"update": 1150,
|
| 2065 |
+
"global_step": 4710400,
|
| 2066 |
+
"num_episodes": 1592,
|
| 2067 |
+
"mean_reward": 33.700903475284576,
|
| 2068 |
+
"mean_length": 2480.53,
|
| 2069 |
+
"loss": 8.177810668945312,
|
| 2070 |
+
"sps": 333.4487379606718
|
| 2071 |
+
},
|
| 2072 |
+
{
|
| 2073 |
+
"update": 1155,
|
| 2074 |
+
"global_step": 4730880,
|
| 2075 |
+
"num_episodes": 1607,
|
| 2076 |
+
"mean_reward": 32.822717969417575,
|
| 2077 |
+
"mean_length": 2485.88,
|
| 2078 |
+
"loss": 58.6836051940918,
|
| 2079 |
+
"sps": 320.2091534142309
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"update": 1160,
|
| 2083 |
+
"global_step": 4751360,
|
| 2084 |
+
"num_episodes": 1613,
|
| 2085 |
+
"mean_reward": 32.850986263751984,
|
| 2086 |
+
"mean_length": 2471.11,
|
| 2087 |
+
"loss": 4.779659748077393,
|
| 2088 |
+
"sps": 886.848895232356
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"update": 1165,
|
| 2092 |
+
"global_step": 4771840,
|
| 2093 |
+
"num_episodes": 1616,
|
| 2094 |
+
"mean_reward": 30.757194340229034,
|
| 2095 |
+
"mean_length": 2379.02,
|
| 2096 |
+
"loss": 0.5000092387199402,
|
| 2097 |
+
"sps": 1201.649782869044
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"update": 1170,
|
| 2101 |
+
"global_step": 4792320,
|
| 2102 |
+
"num_episodes": 1618,
|
| 2103 |
+
"mean_reward": 31.608184831142424,
|
| 2104 |
+
"mean_length": 2481.05,
|
| 2105 |
+
"loss": 0.5737665891647339,
|
| 2106 |
+
"sps": 999.5698665674614
|
| 2107 |
+
},
|
| 2108 |
+
{
|
| 2109 |
+
"update": 1175,
|
| 2110 |
+
"global_step": 4812800,
|
| 2111 |
+
"num_episodes": 1623,
|
| 2112 |
+
"mean_reward": 32.650640833377835,
|
| 2113 |
+
"mean_length": 2658.87,
|
| 2114 |
+
"loss": 3.0942459106445312,
|
| 2115 |
+
"sps": 616.1316245054412
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"update": 1180,
|
| 2119 |
+
"global_step": 4833280,
|
| 2120 |
+
"num_episodes": 1625,
|
| 2121 |
+
"mean_reward": 37.96194513559342,
|
| 2122 |
+
"mean_length": 2682.02,
|
| 2123 |
+
"loss": 9.840081214904785,
|
| 2124 |
+
"sps": 698.9043221988104
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"update": 1185,
|
| 2128 |
+
"global_step": 4853760,
|
| 2129 |
+
"num_episodes": 1630,
|
| 2130 |
+
"mean_reward": 42.92790410280227,
|
| 2131 |
+
"mean_length": 2817.92,
|
| 2132 |
+
"loss": 1.0771808624267578,
|
| 2133 |
+
"sps": 677.5959966787289
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"update": 1190,
|
| 2137 |
+
"global_step": 4874240,
|
| 2138 |
+
"num_episodes": 1631,
|
| 2139 |
+
"mean_reward": 43.29853859186173,
|
| 2140 |
+
"mean_length": 2913.27,
|
| 2141 |
+
"loss": 0.15924929082393646,
|
| 2142 |
+
"sps": 2128.8886043740195
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"update": 1195,
|
| 2146 |
+
"global_step": 4894720,
|
| 2147 |
+
"num_episodes": 1635,
|
| 2148 |
+
"mean_reward": 44.563561956882474,
|
| 2149 |
+
"mean_length": 3101.73,
|
| 2150 |
+
"loss": 24.4128475189209,
|
| 2151 |
+
"sps": 768.3773024267982
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"update": 1200,
|
| 2155 |
+
"global_step": 4915200,
|
| 2156 |
+
"num_episodes": 1642,
|
| 2157 |
+
"mean_reward": 45.34813198566437,
|
| 2158 |
+
"mean_length": 3112.72,
|
| 2159 |
+
"loss": 8.374368667602539,
|
| 2160 |
+
"sps": 976.3571543939305
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"update": 1205,
|
| 2164 |
+
"global_step": 4935680,
|
| 2165 |
+
"num_episodes": 1649,
|
| 2166 |
+
"mean_reward": 46.91295046806336,
|
| 2167 |
+
"mean_length": 3360.16,
|
| 2168 |
+
"loss": 13.855979919433594,
|
| 2169 |
+
"sps": 264.6689562194928
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"update": 1210,
|
| 2173 |
+
"global_step": 4956160,
|
| 2174 |
+
"num_episodes": 1661,
|
| 2175 |
+
"mean_reward": 46.23843379974365,
|
| 2176 |
+
"mean_length": 3281.89,
|
| 2177 |
+
"loss": 95.5245590209961,
|
| 2178 |
+
"sps": 248.04865845009095
|
| 2179 |
+
},
|
| 2180 |
+
{
|
| 2181 |
+
"update": 1215,
|
| 2182 |
+
"global_step": 4976640,
|
| 2183 |
+
"num_episodes": 1669,
|
| 2184 |
+
"mean_reward": 49.53000379562378,
|
| 2185 |
+
"mean_length": 3152.88,
|
| 2186 |
+
"loss": 92.37181091308594,
|
| 2187 |
+
"sps": 241.45699781157901
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"update": 1220,
|
| 2191 |
+
"global_step": 4997120,
|
| 2192 |
+
"num_episodes": 1675,
|
| 2193 |
+
"mean_reward": 49.94117986917496,
|
| 2194 |
+
"mean_length": 3244.89,
|
| 2195 |
+
"loss": 36.136539459228516,
|
| 2196 |
+
"sps": 332.50957910682797
|
| 2197 |
+
},
|
| 2198 |
+
{
|
| 2199 |
+
"update": 1225,
|
| 2200 |
+
"global_step": 5017600,
|
| 2201 |
+
"num_episodes": 1681,
|
| 2202 |
+
"mean_reward": 49.826350367069246,
|
| 2203 |
+
"mean_length": 3322.41,
|
| 2204 |
+
"loss": 4.504380702972412,
|
| 2205 |
+
"sps": 317.38761005771676
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"update": 1230,
|
| 2209 |
+
"global_step": 5038080,
|
| 2210 |
+
"num_episodes": 1686,
|
| 2211 |
+
"mean_reward": 50.16007830858231,
|
| 2212 |
+
"mean_length": 3383.77,
|
| 2213 |
+
"loss": 11.077418327331543,
|
| 2214 |
+
"sps": 614.5178546338719
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"update": 1235,
|
| 2218 |
+
"global_step": 5058560,
|
| 2219 |
+
"num_episodes": 1689,
|
| 2220 |
+
"mean_reward": 50.77651453256607,
|
| 2221 |
+
"mean_length": 3495.66,
|
| 2222 |
+
"loss": 12.558845520019531,
|
| 2223 |
+
"sps": 574.6067562429008
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"update": 1240,
|
| 2227 |
+
"global_step": 5079040,
|
| 2228 |
+
"num_episodes": 1694,
|
| 2229 |
+
"mean_reward": 51.09682610750198,
|
| 2230 |
+
"mean_length": 3719.18,
|
| 2231 |
+
"loss": 21.6842098236084,
|
| 2232 |
+
"sps": 1195.0937330699562
|
| 2233 |
+
},
|
| 2234 |
+
{
|
| 2235 |
+
"update": 1245,
|
| 2236 |
+
"global_step": 5099520,
|
| 2237 |
+
"num_episodes": 1698,
|
| 2238 |
+
"mean_reward": 50.89644577741623,
|
| 2239 |
+
"mean_length": 3737.48,
|
| 2240 |
+
"loss": 65.59449768066406,
|
| 2241 |
+
"sps": 836.6498465651391
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"update": 1250,
|
| 2245 |
+
"global_step": 5120000,
|
| 2246 |
+
"num_episodes": 1701,
|
| 2247 |
+
"mean_reward": 51.103903777599335,
|
| 2248 |
+
"mean_length": 3865.3,
|
| 2249 |
+
"loss": 20.571155548095703,
|
| 2250 |
+
"sps": 835.7550802547468
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"update": 1255,
|
| 2254 |
+
"global_step": 5140480,
|
| 2255 |
+
"num_episodes": 1705,
|
| 2256 |
+
"mean_reward": 56.42267068624496,
|
| 2257 |
+
"mean_length": 4036.09,
|
| 2258 |
+
"loss": 65.08052825927734,
|
| 2259 |
+
"sps": 391.16626869711587
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"update": 1260,
|
| 2263 |
+
"global_step": 5160960,
|
| 2264 |
+
"num_episodes": 1709,
|
| 2265 |
+
"mean_reward": 57.39474864244461,
|
| 2266 |
+
"mean_length": 4054.32,
|
| 2267 |
+
"loss": 9.735504150390625,
|
| 2268 |
+
"sps": 279.94177596903813
|
| 2269 |
+
},
|
| 2270 |
+
{
|
| 2271 |
+
"update": 1265,
|
| 2272 |
+
"global_step": 5181440,
|
| 2273 |
+
"num_episodes": 1715,
|
| 2274 |
+
"mean_reward": 63.1245819735527,
|
| 2275 |
+
"mean_length": 4262.64,
|
| 2276 |
+
"loss": 473.1329040527344,
|
| 2277 |
+
"sps": 195.8880726253604
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"update": 1270,
|
| 2281 |
+
"global_step": 5201920,
|
| 2282 |
+
"num_episodes": 1719,
|
| 2283 |
+
"mean_reward": 56.77260554075241,
|
| 2284 |
+
"mean_length": 4121.23,
|
| 2285 |
+
"loss": 263.35589599609375,
|
| 2286 |
+
"sps": 350.0223876268303
|
| 2287 |
+
},
|
| 2288 |
+
{
|
| 2289 |
+
"update": 1275,
|
| 2290 |
+
"global_step": 5222400,
|
| 2291 |
+
"num_episodes": 1726,
|
| 2292 |
+
"mean_reward": 57.57951702833176,
|
| 2293 |
+
"mean_length": 3960.67,
|
| 2294 |
+
"loss": 59.782310485839844,
|
| 2295 |
+
"sps": 412.90096002367255
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"update": 1280,
|
| 2299 |
+
"global_step": 5242880,
|
| 2300 |
+
"num_episodes": 1736,
|
| 2301 |
+
"mean_reward": 56.08834368228912,
|
| 2302 |
+
"mean_length": 3644.63,
|
| 2303 |
+
"loss": 52.62528991699219,
|
| 2304 |
+
"sps": 343.349341248895
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"update": 1285,
|
| 2308 |
+
"global_step": 5263360,
|
| 2309 |
+
"num_episodes": 1737,
|
| 2310 |
+
"mean_reward": 55.905996737480166,
|
| 2311 |
+
"mean_length": 3640.62,
|
| 2312 |
+
"loss": 104.78556060791016,
|
| 2313 |
+
"sps": 397.8813187415849
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"update": 1290,
|
| 2317 |
+
"global_step": 5283840,
|
| 2318 |
+
"num_episodes": 1746,
|
| 2319 |
+
"mean_reward": 59.82821818828583,
|
| 2320 |
+
"mean_length": 3347.95,
|
| 2321 |
+
"loss": 935.470947265625,
|
| 2322 |
+
"sps": 355.2664513297179
|
| 2323 |
+
},
|
| 2324 |
+
{
|
| 2325 |
+
"update": 1295,
|
| 2326 |
+
"global_step": 5304320,
|
| 2327 |
+
"num_episodes": 1753,
|
| 2328 |
+
"mean_reward": 86.4339063167572,
|
| 2329 |
+
"mean_length": 3459.02,
|
| 2330 |
+
"loss": 795.3289794921875,
|
| 2331 |
+
"sps": 309.51331334453033
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"update": 1300,
|
| 2335 |
+
"global_step": 5324800,
|
| 2336 |
+
"num_episodes": 1762,
|
| 2337 |
+
"mean_reward": 306.1682329654694,
|
| 2338 |
+
"mean_length": 3702.99,
|
| 2339 |
+
"loss": 621.1657104492188,
|
| 2340 |
+
"sps": 312.8076116030221
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"update": 1305,
|
| 2344 |
+
"global_step": 5345280,
|
| 2345 |
+
"num_episodes": 1763,
|
| 2346 |
+
"mean_reward": 306.26519484996794,
|
| 2347 |
+
"mean_length": 3714.28,
|
| 2348 |
+
"loss": 445.75,
|
| 2349 |
+
"sps": 390.84962605893924
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"update": 1310,
|
| 2353 |
+
"global_step": 5365760,
|
| 2354 |
+
"num_episodes": 1772,
|
| 2355 |
+
"mean_reward": 357.3265011548996,
|
| 2356 |
+
"mean_length": 3776.52,
|
| 2357 |
+
"loss": 1374.097412109375,
|
| 2358 |
+
"sps": 385.8458185201923
|
| 2359 |
+
},
|
| 2360 |
+
{
|
| 2361 |
+
"update": 1315,
|
| 2362 |
+
"global_step": 5386240,
|
| 2363 |
+
"num_episodes": 1773,
|
| 2364 |
+
"mean_reward": 357.70143792629244,
|
| 2365 |
+
"mean_length": 3875.1,
|
| 2366 |
+
"loss": 208.59083557128906,
|
| 2367 |
+
"sps": 555.0694538042676
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"update": 1320,
|
| 2371 |
+
"global_step": 5406720,
|
| 2372 |
+
"num_episodes": 1786,
|
| 2373 |
+
"mean_reward": 362.7652148580551,
|
| 2374 |
+
"mean_length": 3706.89,
|
| 2375 |
+
"loss": 1506.414306640625,
|
| 2376 |
+
"sps": 246.7002255816469
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"update": 1325,
|
| 2380 |
+
"global_step": 5427200,
|
| 2381 |
+
"num_episodes": 1786,
|
| 2382 |
+
"mean_reward": 362.7652148580551,
|
| 2383 |
+
"mean_length": 3706.89,
|
| 2384 |
+
"loss": 46.25688934326172,
|
| 2385 |
+
"sps": 409.5117865802824
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"update": 1330,
|
| 2389 |
+
"global_step": 5447680,
|
| 2390 |
+
"num_episodes": 1791,
|
| 2391 |
+
"mean_reward": 501.35476023197174,
|
| 2392 |
+
"mean_length": 3744.98,
|
| 2393 |
+
"loss": 371.16973876953125,
|
| 2394 |
+
"sps": 278.5499936271881
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"update": 1335,
|
| 2398 |
+
"global_step": 5468160,
|
| 2399 |
+
"num_episodes": 1793,
|
| 2400 |
+
"mean_reward": 607.4379647493363,
|
| 2401 |
+
"mean_length": 3921.02,
|
| 2402 |
+
"loss": 73.33538818359375,
|
| 2403 |
+
"sps": 388.619707385681
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"update": 1340,
|
| 2407 |
+
"global_step": 5488640,
|
| 2408 |
+
"num_episodes": 1796,
|
| 2409 |
+
"mean_reward": 756.3367283582687,
|
| 2410 |
+
"mean_length": 4020.31,
|
| 2411 |
+
"loss": 462.8284606933594,
|
| 2412 |
+
"sps": 342.5094025627594
|
| 2413 |
+
},
|
| 2414 |
+
{
|
| 2415 |
+
"update": 1345,
|
| 2416 |
+
"global_step": 5509120,
|
| 2417 |
+
"num_episodes": 1796,
|
| 2418 |
+
"mean_reward": 756.3367283582687,
|
| 2419 |
+
"mean_length": 4020.31,
|
| 2420 |
+
"loss": 67.39126586914062,
|
| 2421 |
+
"sps": 385.48904917796193
|
| 2422 |
+
},
|
| 2423 |
+
{
|
| 2424 |
+
"update": 1350,
|
| 2425 |
+
"global_step": 5529600,
|
| 2426 |
+
"num_episodes": 1802,
|
| 2427 |
+
"mean_reward": 869.4895800352097,
|
| 2428 |
+
"mean_length": 3967.21,
|
| 2429 |
+
"loss": 12.0632905960083,
|
| 2430 |
+
"sps": 668.8793003173347
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"update": 1355,
|
| 2434 |
+
"global_step": 5550080,
|
| 2435 |
+
"num_episodes": 1804,
|
| 2436 |
+
"mean_reward": 989.9085026121139,
|
| 2437 |
+
"mean_length": 4063.23,
|
| 2438 |
+
"loss": 86.83934783935547,
|
| 2439 |
+
"sps": 418.3353031686608
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"update": 1360,
|
| 2443 |
+
"global_step": 5570560,
|
| 2444 |
+
"num_episodes": 1815,
|
| 2445 |
+
"mean_reward": 1078.798788728714,
|
| 2446 |
+
"mean_length": 3886.21,
|
| 2447 |
+
"loss": 666.8345336914062,
|
| 2448 |
+
"sps": 256.51104316818095
|
| 2449 |
+
},
|
| 2450 |
+
{
|
| 2451 |
+
"update": 1365,
|
| 2452 |
+
"global_step": 5591040,
|
| 2453 |
+
"num_episodes": 1815,
|
| 2454 |
+
"mean_reward": 1078.798788728714,
|
| 2455 |
+
"mean_length": 3886.21,
|
| 2456 |
+
"loss": 900.6356811523438,
|
| 2457 |
+
"sps": 495.47242571130397
|
| 2458 |
+
},
|
| 2459 |
+
{
|
| 2460 |
+
"update": 1370,
|
| 2461 |
+
"global_step": 5611520,
|
| 2462 |
+
"num_episodes": 1824,
|
| 2463 |
+
"mean_reward": 1200.6963546466827,
|
| 2464 |
+
"mean_length": 4027.44,
|
| 2465 |
+
"loss": 20.821474075317383,
|
| 2466 |
+
"sps": 506.7840907522114
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"update": 1375,
|
| 2470 |
+
"global_step": 5632000,
|
| 2471 |
+
"num_episodes": 1826,
|
| 2472 |
+
"mean_reward": 1261.5812614822387,
|
| 2473 |
+
"mean_length": 4015.04,
|
| 2474 |
+
"loss": 4563.7763671875,
|
| 2475 |
+
"sps": 675.537157736375
|
| 2476 |
+
},
|
| 2477 |
+
{
|
| 2478 |
+
"update": 1380,
|
| 2479 |
+
"global_step": 5652480,
|
| 2480 |
+
"num_episodes": 1836,
|
| 2481 |
+
"mean_reward": 1445.384720082283,
|
| 2482 |
+
"mean_length": 4027.89,
|
| 2483 |
+
"loss": 459.9952697753906,
|
| 2484 |
+
"sps": 341.6139254031597
|
| 2485 |
+
},
|
| 2486 |
+
{
|
| 2487 |
+
"update": 1385,
|
| 2488 |
+
"global_step": 5672960,
|
| 2489 |
+
"num_episodes": 1839,
|
| 2490 |
+
"mean_reward": 1445.7170259952545,
|
| 2491 |
+
"mean_length": 4039.25,
|
| 2492 |
+
"loss": 1.4308533668518066,
|
| 2493 |
+
"sps": 1488.9461962855103
|
| 2494 |
+
},
|
| 2495 |
+
{
|
| 2496 |
+
"update": 1390,
|
| 2497 |
+
"global_step": 5693440,
|
| 2498 |
+
"num_episodes": 1856,
|
| 2499 |
+
"mean_reward": 1429.1698562908173,
|
| 2500 |
+
"mean_length": 3901.28,
|
| 2501 |
+
"loss": 13.810539245605469,
|
| 2502 |
+
"sps": 583.7912153704766
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"update": 1395,
|
| 2506 |
+
"global_step": 5713920,
|
| 2507 |
+
"num_episodes": 1863,
|
| 2508 |
+
"mean_reward": 1209.2014095544814,
|
| 2509 |
+
"mean_length": 3639.94,
|
| 2510 |
+
"loss": 273.29278564453125,
|
| 2511 |
+
"sps": 645.3489718832685
|
| 2512 |
+
},
|
| 2513 |
+
{
|
| 2514 |
+
"update": 1400,
|
| 2515 |
+
"global_step": 5734400,
|
| 2516 |
+
"num_episodes": 1871,
|
| 2517 |
+
"mean_reward": 1319.8262105464935,
|
| 2518 |
+
"mean_length": 3745.57,
|
| 2519 |
+
"loss": 16.14458656311035,
|
| 2520 |
+
"sps": 324.31654457005965
|
| 2521 |
+
},
|
| 2522 |
+
{
|
| 2523 |
+
"update": 1405,
|
| 2524 |
+
"global_step": 5754880,
|
| 2525 |
+
"num_episodes": 1887,
|
| 2526 |
+
"mean_reward": 1180.7784528923034,
|
| 2527 |
+
"mean_length": 3295.57,
|
| 2528 |
+
"loss": 3.5345799922943115,
|
| 2529 |
+
"sps": 635.0555390978727
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"update": 1410,
|
| 2533 |
+
"global_step": 5775360,
|
| 2534 |
+
"num_episodes": 1897,
|
| 2535 |
+
"mean_reward": 920.7941575908661,
|
| 2536 |
+
"mean_length": 2829.74,
|
| 2537 |
+
"loss": 29.106164932250977,
|
| 2538 |
+
"sps": 283.5497895518039
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"update": 1415,
|
| 2542 |
+
"global_step": 5795840,
|
| 2543 |
+
"num_episodes": 1899,
|
| 2544 |
+
"mean_reward": 1015.2013060569764,
|
| 2545 |
+
"mean_length": 2877.24,
|
| 2546 |
+
"loss": 134.17953491210938,
|
| 2547 |
+
"sps": 514.4558919437959
|
| 2548 |
+
},
|
| 2549 |
+
{
|
| 2550 |
+
"update": 1420,
|
| 2551 |
+
"global_step": 5816320,
|
| 2552 |
+
"num_episodes": 1905,
|
| 2553 |
+
"mean_reward": 759.3930412435532,
|
| 2554 |
+
"mean_length": 2493.3,
|
| 2555 |
+
"loss": 71.0991439819336,
|
| 2556 |
+
"sps": 407.36350916126725
|
| 2557 |
+
},
|
| 2558 |
+
{
|
| 2559 |
+
"update": 1425,
|
| 2560 |
+
"global_step": 5836800,
|
| 2561 |
+
"num_episodes": 1923,
|
| 2562 |
+
"mean_reward": 591.994899687767,
|
| 2563 |
+
"mean_length": 2306.11,
|
| 2564 |
+
"loss": 665.6765747070312,
|
| 2565 |
+
"sps": 292.25754672826326
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"update": 1430,
|
| 2569 |
+
"global_step": 5857280,
|
| 2570 |
+
"num_episodes": 1926,
|
| 2571 |
+
"mean_reward": 491.9243581056595,
|
| 2572 |
+
"mean_length": 2308.91,
|
| 2573 |
+
"loss": 97.95196533203125,
|
| 2574 |
+
"sps": 398.43841528471495
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"update": 1435,
|
| 2578 |
+
"global_step": 5877760,
|
| 2579 |
+
"num_episodes": 1934,
|
| 2580 |
+
"mean_reward": 396.85663065433505,
|
| 2581 |
+
"mean_length": 2257.74,
|
| 2582 |
+
"loss": 1123.9271240234375,
|
| 2583 |
+
"sps": 467.5370774012981
|
| 2584 |
+
},
|
| 2585 |
+
{
|
| 2586 |
+
"update": 1440,
|
| 2587 |
+
"global_step": 5898240,
|
| 2588 |
+
"num_episodes": 1939,
|
| 2589 |
+
"mean_reward": 444.68491759777066,
|
| 2590 |
+
"mean_length": 2252.07,
|
| 2591 |
+
"loss": 149.9423065185547,
|
| 2592 |
+
"sps": 397.96294200167154
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"update": 1445,
|
| 2596 |
+
"global_step": 5918720,
|
| 2597 |
+
"num_episodes": 1952,
|
| 2598 |
+
"mean_reward": 490.6093361234665,
|
| 2599 |
+
"mean_length": 2347.41,
|
| 2600 |
+
"loss": 188.90318298339844,
|
| 2601 |
+
"sps": 433.4020614000179
|
| 2602 |
+
},
|
| 2603 |
+
{
|
| 2604 |
+
"update": 1450,
|
| 2605 |
+
"global_step": 5939200,
|
| 2606 |
+
"num_episodes": 1968,
|
| 2607 |
+
"mean_reward": 341.27103984832763,
|
| 2608 |
+
"mean_length": 2088.38,
|
| 2609 |
+
"loss": 49.23589324951172,
|
| 2610 |
+
"sps": 192.3194868778508
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"update": 1455,
|
| 2614 |
+
"global_step": 5959680,
|
| 2615 |
+
"num_episodes": 1980,
|
| 2616 |
+
"mean_reward": 340.5469175004959,
|
| 2617 |
+
"mean_length": 2102.8,
|
| 2618 |
+
"loss": 53.03819274902344,
|
| 2619 |
+
"sps": 401.45828106312945
|
| 2620 |
+
},
|
| 2621 |
+
{
|
| 2622 |
+
"update": 1460,
|
| 2623 |
+
"global_step": 5980160,
|
| 2624 |
+
"num_episodes": 1987,
|
| 2625 |
+
"mean_reward": 341.23766746520994,
|
| 2626 |
+
"mean_length": 2290.56,
|
| 2627 |
+
"loss": 12.17508316040039,
|
| 2628 |
+
"sps": 321.48619942614465
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"update": 1465,
|
| 2632 |
+
"global_step": 6000640,
|
| 2633 |
+
"num_episodes": 1993,
|
| 2634 |
+
"mean_reward": 340.6004219532013,
|
| 2635 |
+
"mean_length": 2289.4,
|
| 2636 |
+
"loss": 4.770975589752197,
|
| 2637 |
+
"sps": 400.6137968711218
|
| 2638 |
+
},
|
| 2639 |
+
{
|
| 2640 |
+
"update": 1470,
|
| 2641 |
+
"global_step": 6021120,
|
| 2642 |
+
"num_episodes": 2004,
|
| 2643 |
+
"mean_reward": 321.17223945140836,
|
| 2644 |
+
"mean_length": 2148.56,
|
| 2645 |
+
"loss": 29.761117935180664,
|
| 2646 |
+
"sps": 472.58742855602395
|
| 2647 |
+
},
|
| 2648 |
+
{
|
| 2649 |
+
"update": 1475,
|
| 2650 |
+
"global_step": 6041600,
|
| 2651 |
+
"num_episodes": 2026,
|
| 2652 |
+
"mean_reward": 336.3226027822495,
|
| 2653 |
+
"mean_length": 1952.34,
|
| 2654 |
+
"loss": 203.31748962402344,
|
| 2655 |
+
"sps": 357.29518794795473
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"update": 1480,
|
| 2659 |
+
"global_step": 6062080,
|
| 2660 |
+
"num_episodes": 2033,
|
| 2661 |
+
"mean_reward": 313.32783755540845,
|
| 2662 |
+
"mean_length": 1958.32,
|
| 2663 |
+
"loss": 508.1851501464844,
|
| 2664 |
+
"sps": 510.89708007010705
|
| 2665 |
+
},
|
| 2666 |
+
{
|
| 2667 |
+
"update": 1485,
|
| 2668 |
+
"global_step": 6082560,
|
| 2669 |
+
"num_episodes": 2046,
|
| 2670 |
+
"mean_reward": 194.68075824975966,
|
| 2671 |
+
"mean_length": 1639.76,
|
| 2672 |
+
"loss": 7.842682361602783,
|
| 2673 |
+
"sps": 546.9033062498472
|
| 2674 |
+
},
|
| 2675 |
+
{
|
| 2676 |
+
"update": 1490,
|
| 2677 |
+
"global_step": 6103040,
|
| 2678 |
+
"num_episodes": 2050,
|
| 2679 |
+
"mean_reward": 143.90823694944382,
|
| 2680 |
+
"mean_length": 1738.66,
|
| 2681 |
+
"loss": 46.426143646240234,
|
| 2682 |
+
"sps": 306.85539615127885
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"update": 1495,
|
| 2686 |
+
"global_step": 6123520,
|
| 2687 |
+
"num_episodes": 2060,
|
| 2688 |
+
"mean_reward": 334.49683523893356,
|
| 2689 |
+
"mean_length": 1898.53,
|
| 2690 |
+
"loss": 468.38525390625,
|
| 2691 |
+
"sps": 245.82053873712613
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"update": 1500,
|
| 2695 |
+
"global_step": 6144000,
|
| 2696 |
+
"num_episodes": 2069,
|
| 2697 |
+
"mean_reward": 334.39896435022354,
|
| 2698 |
+
"mean_length": 2044.37,
|
| 2699 |
+
"loss": 85.75762939453125,
|
| 2700 |
+
"sps": 334.1080989119973
|
| 2701 |
+
},
|
| 2702 |
+
{
|
| 2703 |
+
"update": 1505,
|
| 2704 |
+
"global_step": 6164480,
|
| 2705 |
+
"num_episodes": 2074,
|
| 2706 |
+
"mean_reward": 333.67030994653703,
|
| 2707 |
+
"mean_length": 1990.3,
|
| 2708 |
+
"loss": 295.0758361816406,
|
| 2709 |
+
"sps": 345.61576592839117
|
| 2710 |
+
},
|
| 2711 |
+
{
|
| 2712 |
+
"update": 1510,
|
| 2713 |
+
"global_step": 6184960,
|
| 2714 |
+
"num_episodes": 2080,
|
| 2715 |
+
"mean_reward": 334.66018194913863,
|
| 2716 |
+
"mean_length": 2150.39,
|
| 2717 |
+
"loss": 10.077195167541504,
|
| 2718 |
+
"sps": 420.2391860174057
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"update": 1515,
|
| 2722 |
+
"global_step": 6205440,
|
| 2723 |
+
"num_episodes": 2097,
|
| 2724 |
+
"mean_reward": 258.6993135094643,
|
| 2725 |
+
"mean_length": 2109.74,
|
| 2726 |
+
"loss": 122.61629486083984,
|
| 2727 |
+
"sps": 229.56375224355847
|
| 2728 |
+
},
|
| 2729 |
+
{
|
| 2730 |
+
"update": 1520,
|
| 2731 |
+
"global_step": 6225920,
|
| 2732 |
+
"num_episodes": 2107,
|
| 2733 |
+
"mean_reward": 258.4274232983589,
|
| 2734 |
+
"mean_length": 2108.42,
|
| 2735 |
+
"loss": 361.1533203125,
|
| 2736 |
+
"sps": 361.8525022786034
|
| 2737 |
+
},
|
| 2738 |
+
{
|
| 2739 |
+
"update": 1525,
|
| 2740 |
+
"global_step": 6246400,
|
| 2741 |
+
"num_episodes": 2125,
|
| 2742 |
+
"mean_reward": 239.45979365587235,
|
| 2743 |
+
"mean_length": 1883.93,
|
| 2744 |
+
"loss": 25.989086151123047,
|
| 2745 |
+
"sps": 275.38397015212564
|
| 2746 |
+
},
|
| 2747 |
+
{
|
| 2748 |
+
"update": 1530,
|
| 2749 |
+
"global_step": 6266880,
|
| 2750 |
+
"num_episodes": 2131,
|
| 2751 |
+
"mean_reward": 239.8594556736946,
|
| 2752 |
+
"mean_length": 1981.69,
|
| 2753 |
+
"loss": 404.8509521484375,
|
| 2754 |
+
"sps": 405.6766540706019
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"update": 1535,
|
| 2758 |
+
"global_step": 6287360,
|
| 2759 |
+
"num_episodes": 2146,
|
| 2760 |
+
"mean_reward": 303.8745777082443,
|
| 2761 |
+
"mean_length": 2254.68,
|
| 2762 |
+
"loss": 1170.5218505859375,
|
| 2763 |
+
"sps": 251.0949486970236
|
| 2764 |
+
},
|
| 2765 |
+
{
|
| 2766 |
+
"update": 1540,
|
| 2767 |
+
"global_step": 6307840,
|
| 2768 |
+
"num_episodes": 2147,
|
| 2769 |
+
"mean_reward": 304.0846936607361,
|
| 2770 |
+
"mean_length": 2341.33,
|
| 2771 |
+
"loss": 8.5966157913208,
|
| 2772 |
+
"sps": 446.2390266117631
|
| 2773 |
+
},
|
| 2774 |
+
{
|
| 2775 |
+
"update": 1545,
|
| 2776 |
+
"global_step": 6328320,
|
| 2777 |
+
"num_episodes": 2154,
|
| 2778 |
+
"mean_reward": 437.3326745700836,
|
| 2779 |
+
"mean_length": 2280.45,
|
| 2780 |
+
"loss": 1299.16552734375,
|
| 2781 |
+
"sps": 259.202559576872
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"update": 1550,
|
| 2785 |
+
"global_step": 6348800,
|
| 2786 |
+
"num_episodes": 2158,
|
| 2787 |
+
"mean_reward": 303.4427977991104,
|
| 2788 |
+
"mean_length": 2211.31,
|
| 2789 |
+
"loss": 1.1450996398925781,
|
| 2790 |
+
"sps": 549.5109518078744
|
| 2791 |
+
},
|
| 2792 |
+
{
|
| 2793 |
+
"update": 1555,
|
| 2794 |
+
"global_step": 6369280,
|
| 2795 |
+
"num_episodes": 2172,
|
| 2796 |
+
"mean_reward": 304.4946458005905,
|
| 2797 |
+
"mean_length": 2210.89,
|
| 2798 |
+
"loss": 59.038814544677734,
|
| 2799 |
+
"sps": 341.25380949315337
|
| 2800 |
+
},
|
| 2801 |
+
{
|
| 2802 |
+
"update": 1560,
|
| 2803 |
+
"global_step": 6389760,
|
| 2804 |
+
"num_episodes": 2175,
|
| 2805 |
+
"mean_reward": 304.3582187414169,
|
| 2806 |
+
"mean_length": 2211.87,
|
| 2807 |
+
"loss": 13.61323070526123,
|
| 2808 |
+
"sps": 642.8393173099237
|
| 2809 |
+
},
|
| 2810 |
+
{
|
| 2811 |
+
"update": 1565,
|
| 2812 |
+
"global_step": 6410240,
|
| 2813 |
+
"num_episodes": 2180,
|
| 2814 |
+
"mean_reward": 305.09624064445495,
|
| 2815 |
+
"mean_length": 2307.71,
|
| 2816 |
+
"loss": 1913.05126953125,
|
| 2817 |
+
"sps": 391.8241680446758
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"update": 1570,
|
| 2821 |
+
"global_step": 6430720,
|
| 2822 |
+
"num_episodes": 2183,
|
| 2823 |
+
"mean_reward": 305.77074447154996,
|
| 2824 |
+
"mean_length": 2405.35,
|
| 2825 |
+
"loss": 136.88858032226562,
|
| 2826 |
+
"sps": 394.7672396028363
|
| 2827 |
+
},
|
| 2828 |
+
{
|
| 2829 |
+
"update": 1575,
|
| 2830 |
+
"global_step": 6451200,
|
| 2831 |
+
"num_episodes": 2189,
|
| 2832 |
+
"mean_reward": 405.41952825069427,
|
| 2833 |
+
"mean_length": 2593.85,
|
| 2834 |
+
"loss": 83.12802124023438,
|
| 2835 |
+
"sps": 299.9621165564932
|
| 2836 |
+
},
|
| 2837 |
+
{
|
| 2838 |
+
"update": 1580,
|
| 2839 |
+
"global_step": 6471680,
|
| 2840 |
+
"num_episodes": 2207,
|
| 2841 |
+
"mean_reward": 405.9634767389297,
|
| 2842 |
+
"mean_length": 2524.02,
|
| 2843 |
+
"loss": 13081.1357421875,
|
| 2844 |
+
"sps": 223.53810669328672
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"update": 1585,
|
| 2848 |
+
"global_step": 6492160,
|
| 2849 |
+
"num_episodes": 2211,
|
| 2850 |
+
"mean_reward": 499.87862377643586,
|
| 2851 |
+
"mean_length": 2495.58,
|
| 2852 |
+
"loss": 46.772918701171875,
|
| 2853 |
+
"sps": 453.36473969791376
|
| 2854 |
+
},
|
| 2855 |
+
{
|
| 2856 |
+
"update": 1590,
|
| 2857 |
+
"global_step": 6512640,
|
| 2858 |
+
"num_episodes": 2221,
|
| 2859 |
+
"mean_reward": 670.4232928800583,
|
| 2860 |
+
"mean_length": 2706.97,
|
| 2861 |
+
"loss": 368.63763427734375,
|
| 2862 |
+
"sps": 429.39001544641116
|
| 2863 |
+
},
|
| 2864 |
+
{
|
| 2865 |
+
"update": 1595,
|
| 2866 |
+
"global_step": 6533120,
|
| 2867 |
+
"num_episodes": 2227,
|
| 2868 |
+
"mean_reward": 803.7308926296234,
|
| 2869 |
+
"mean_length": 2725.72,
|
| 2870 |
+
"loss": 90.26509094238281,
|
| 2871 |
+
"sps": 413.30646156887036
|
| 2872 |
+
},
|
| 2873 |
+
{
|
| 2874 |
+
"update": 1600,
|
| 2875 |
+
"global_step": 6553600,
|
| 2876 |
+
"num_episodes": 2232,
|
| 2877 |
+
"mean_reward": 933.0243373584748,
|
| 2878 |
+
"mean_length": 2915.95,
|
| 2879 |
+
"loss": 68.28546142578125,
|
| 2880 |
+
"sps": 374.56623534825485
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"update": 1605,
|
| 2884 |
+
"global_step": 6574080,
|
| 2885 |
+
"num_episodes": 2235,
|
| 2886 |
+
"mean_reward": 933.269734544754,
|
| 2887 |
+
"mean_length": 2912.74,
|
| 2888 |
+
"loss": 865.8887939453125,
|
| 2889 |
+
"sps": 445.657946827829
|
| 2890 |
+
},
|
| 2891 |
+
{
|
| 2892 |
+
"update": 1610,
|
| 2893 |
+
"global_step": 6594560,
|
| 2894 |
+
"num_episodes": 2237,
|
| 2895 |
+
"mean_reward": 933.7870253133774,
|
| 2896 |
+
"mean_length": 3011.88,
|
| 2897 |
+
"loss": 871.9052734375,
|
| 2898 |
+
"sps": 387.41989720305287
|
| 2899 |
+
},
|
| 2900 |
+
{
|
| 2901 |
+
"update": 1615,
|
| 2902 |
+
"global_step": 6615040,
|
| 2903 |
+
"num_episodes": 2248,
|
| 2904 |
+
"mean_reward": 1077.8849126005173,
|
| 2905 |
+
"mean_length": 3056.53,
|
| 2906 |
+
"loss": 54.994510650634766,
|
| 2907 |
+
"sps": 423.33621401282124
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"update": 1620,
|
| 2911 |
+
"global_step": 6635520,
|
| 2912 |
+
"num_episodes": 2258,
|
| 2913 |
+
"mean_reward": 943.9673701143265,
|
| 2914 |
+
"mean_length": 3023.43,
|
| 2915 |
+
"loss": 137.88092041015625,
|
| 2916 |
+
"sps": 374.57440205325895
|
| 2917 |
+
},
|
| 2918 |
+
{
|
| 2919 |
+
"update": 1625,
|
| 2920 |
+
"global_step": 6656000,
|
| 2921 |
+
"num_episodes": 2263,
|
| 2922 |
+
"mean_reward": 856.1039279556275,
|
| 2923 |
+
"mean_length": 2924.57,
|
| 2924 |
+
"loss": 348.59234619140625,
|
| 2925 |
+
"sps": 377.6081162361363
|
| 2926 |
+
},
|
| 2927 |
+
{
|
| 2928 |
+
"update": 1630,
|
| 2929 |
+
"global_step": 6676480,
|
| 2930 |
+
"num_episodes": 2267,
|
| 2931 |
+
"mean_reward": 931.3061418437958,
|
| 2932 |
+
"mean_length": 2926.62,
|
| 2933 |
+
"loss": 9.557199478149414,
|
| 2934 |
+
"sps": 460.1107258733158
|
| 2935 |
+
},
|
| 2936 |
+
{
|
| 2937 |
+
"update": 1635,
|
| 2938 |
+
"global_step": 6696960,
|
| 2939 |
+
"num_episodes": 2273,
|
| 2940 |
+
"mean_reward": 931.8358981752395,
|
| 2941 |
+
"mean_length": 3120.06,
|
| 2942 |
+
"loss": 514.8411254882812,
|
| 2943 |
+
"sps": 523.5469529045816
|
| 2944 |
+
},
|
| 2945 |
+
{
|
| 2946 |
+
"update": 1640,
|
| 2947 |
+
"global_step": 6717440,
|
| 2948 |
+
"num_episodes": 2276,
|
| 2949 |
+
"mean_reward": 1109.3497059488298,
|
| 2950 |
+
"mean_length": 3219.09,
|
| 2951 |
+
"loss": 31.73206329345703,
|
| 2952 |
+
"sps": 412.7885853043598
|
| 2953 |
+
},
|
| 2954 |
+
{
|
| 2955 |
+
"update": 1645,
|
| 2956 |
+
"global_step": 6737920,
|
| 2957 |
+
"num_episodes": 2282,
|
| 2958 |
+
"mean_reward": 1197.9563966131211,
|
| 2959 |
+
"mean_length": 3220.5,
|
| 2960 |
+
"loss": 35.86986541748047,
|
| 2961 |
+
"sps": 466.28907053794126
|
| 2962 |
+
},
|
| 2963 |
+
{
|
| 2964 |
+
"update": 1650,
|
| 2965 |
+
"global_step": 6758400,
|
| 2966 |
+
"num_episodes": 2285,
|
| 2967 |
+
"mean_reward": 1119.968164858818,
|
| 2968 |
+
"mean_length": 3067.54,
|
| 2969 |
+
"loss": 279.3809509277344,
|
| 2970 |
+
"sps": 415.9298164658184
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"update": 1655,
|
| 2974 |
+
"global_step": 6778880,
|
| 2975 |
+
"num_episodes": 2299,
|
| 2976 |
+
"mean_reward": 1277.0260197210312,
|
| 2977 |
+
"mean_length": 3026.13,
|
| 2978 |
+
"loss": 44.909996032714844,
|
| 2979 |
+
"sps": 289.10855632711406
|
| 2980 |
+
},
|
| 2981 |
+
{
|
| 2982 |
+
"update": 1660,
|
| 2983 |
+
"global_step": 6799360,
|
| 2984 |
+
"num_episodes": 2310,
|
| 2985 |
+
"mean_reward": 1212.9116531801224,
|
| 2986 |
+
"mean_length": 3157.69,
|
| 2987 |
+
"loss": 19.89190673828125,
|
| 2988 |
+
"sps": 442.19954156582503
|
| 2989 |
+
},
|
| 2990 |
+
{
|
| 2991 |
+
"update": 1665,
|
| 2992 |
+
"global_step": 6819840,
|
| 2993 |
+
"num_episodes": 2313,
|
| 2994 |
+
"mean_reward": 1237.1113989305495,
|
| 2995 |
+
"mean_length": 3267.66,
|
| 2996 |
+
"loss": 49.466552734375,
|
| 2997 |
+
"sps": 941.6208281097553
|
| 2998 |
+
},
|
| 2999 |
+
{
|
| 3000 |
+
"update": 1670,
|
| 3001 |
+
"global_step": 6840320,
|
| 3002 |
+
"num_episodes": 2320,
|
| 3003 |
+
"mean_reward": 1185.366361656189,
|
| 3004 |
+
"mean_length": 3170.05,
|
| 3005 |
+
"loss": 226.9459686279297,
|
| 3006 |
+
"sps": 560.8755073464478
|
| 3007 |
+
},
|
| 3008 |
+
{
|
| 3009 |
+
"update": 1675,
|
| 3010 |
+
"global_step": 6860800,
|
| 3011 |
+
"num_episodes": 2327,
|
| 3012 |
+
"mean_reward": 1171.2066772079468,
|
| 3013 |
+
"mean_length": 3355.09,
|
| 3014 |
+
"loss": 10.15625,
|
| 3015 |
+
"sps": 335.8002299447698
|
| 3016 |
+
},
|
| 3017 |
+
{
|
| 3018 |
+
"update": 1680,
|
| 3019 |
+
"global_step": 6881280,
|
| 3020 |
+
"num_episodes": 2333,
|
| 3021 |
+
"mean_reward": 1042.0874049663544,
|
| 3022 |
+
"mean_length": 3211.85,
|
| 3023 |
+
"loss": 82.60301971435547,
|
| 3024 |
+
"sps": 302.2235800221304
|
| 3025 |
+
},
|
| 3026 |
+
{
|
| 3027 |
+
"update": 1685,
|
| 3028 |
+
"global_step": 6901760,
|
| 3029 |
+
"num_episodes": 2339,
|
| 3030 |
+
"mean_reward": 972.5269057083129,
|
| 3031 |
+
"mean_length": 3193.44,
|
| 3032 |
+
"loss": 120.32151794433594,
|
| 3033 |
+
"sps": 664.7036679347333
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"update": 1690,
|
| 3037 |
+
"global_step": 6922240,
|
| 3038 |
+
"num_episodes": 2339,
|
| 3039 |
+
"mean_reward": 972.5269057083129,
|
| 3040 |
+
"mean_length": 3193.44,
|
| 3041 |
+
"loss": 1.7924470901489258,
|
| 3042 |
+
"sps": 1063.7604928109242
|
| 3043 |
+
},
|
| 3044 |
+
{
|
| 3045 |
+
"update": 1695,
|
| 3046 |
+
"global_step": 6942720,
|
| 3047 |
+
"num_episodes": 2342,
|
| 3048 |
+
"mean_reward": 942.9001926231384,
|
| 3049 |
+
"mean_length": 3342.44,
|
| 3050 |
+
"loss": 6.127931594848633,
|
| 3051 |
+
"sps": 592.3562356846871
|
| 3052 |
+
},
|
| 3053 |
+
{
|
| 3054 |
+
"update": 1700,
|
| 3055 |
+
"global_step": 6963200,
|
| 3056 |
+
"num_episodes": 2345,
|
| 3057 |
+
"mean_reward": 943.6058731651306,
|
| 3058 |
+
"mean_length": 3474.03,
|
| 3059 |
+
"loss": 44.08333206176758,
|
| 3060 |
+
"sps": 297.44937442353597
|
| 3061 |
+
},
|
| 3062 |
+
{
|
| 3063 |
+
"update": 1705,
|
| 3064 |
+
"global_step": 6983680,
|
| 3065 |
+
"num_episodes": 2350,
|
| 3066 |
+
"mean_reward": 891.2378608131409,
|
| 3067 |
+
"mean_length": 3613.22,
|
| 3068 |
+
"loss": 139.50340270996094,
|
| 3069 |
+
"sps": 321.276001001162
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"update": 1710,
|
| 3073 |
+
"global_step": 7004160,
|
| 3074 |
+
"num_episodes": 2351,
|
| 3075 |
+
"mean_reward": 891.2994220161438,
|
| 3076 |
+
"mean_length": 3670.58,
|
| 3077 |
+
"loss": 80.7029800415039,
|
| 3078 |
+
"sps": 602.1302177845877
|
| 3079 |
+
},
|
| 3080 |
+
{
|
| 3081 |
+
"update": 1715,
|
| 3082 |
+
"global_step": 7024640,
|
| 3083 |
+
"num_episodes": 2354,
|
| 3084 |
+
"mean_reward": 891.3987969732284,
|
| 3085 |
+
"mean_length": 3707.87,
|
| 3086 |
+
"loss": 43.55419921875,
|
| 3087 |
+
"sps": 609.1286236648131
|
| 3088 |
+
},
|
| 3089 |
+
{
|
| 3090 |
+
"update": 1720,
|
| 3091 |
+
"global_step": 7045120,
|
| 3092 |
+
"num_episodes": 2356,
|
| 3093 |
+
"mean_reward": 908.0675931024551,
|
| 3094 |
+
"mean_length": 3894.63,
|
| 3095 |
+
"loss": 1924.8736572265625,
|
| 3096 |
+
"sps": 521.5708115336275
|
| 3097 |
+
},
|
| 3098 |
+
{
|
| 3099 |
+
"update": 1725,
|
| 3100 |
+
"global_step": 7065600,
|
| 3101 |
+
"num_episodes": 2368,
|
| 3102 |
+
"mean_reward": 877.4067792797089,
|
| 3103 |
+
"mean_length": 4024.38,
|
| 3104 |
+
"loss": 1546.024658203125,
|
| 3105 |
+
"sps": 144.1450251623922
|
| 3106 |
+
},
|
| 3107 |
+
{
|
| 3108 |
+
"update": 1730,
|
| 3109 |
+
"global_step": 7086080,
|
| 3110 |
+
"num_episodes": 2371,
|
| 3111 |
+
"mean_reward": 876.8285467529297,
|
| 3112 |
+
"mean_length": 4001.29,
|
| 3113 |
+
"loss": 140.04344177246094,
|
| 3114 |
+
"sps": 219.3887746950412
|
| 3115 |
+
},
|
| 3116 |
+
{
|
| 3117 |
+
"update": 1735,
|
| 3118 |
+
"global_step": 7106560,
|
| 3119 |
+
"num_episodes": 2379,
|
| 3120 |
+
"mean_reward": 712.0810299873352,
|
| 3121 |
+
"mean_length": 3765.17,
|
| 3122 |
+
"loss": 592.1142578125,
|
| 3123 |
+
"sps": 154.4538739502226
|
| 3124 |
+
},
|
| 3125 |
+
{
|
| 3126 |
+
"update": 1740,
|
| 3127 |
+
"global_step": 7127040,
|
| 3128 |
+
"num_episodes": 2380,
|
| 3129 |
+
"mean_reward": 711.973635725975,
|
| 3130 |
+
"mean_length": 3803.94,
|
| 3131 |
+
"loss": 94.82659149169922,
|
| 3132 |
+
"sps": 312.59798550353105
|
| 3133 |
+
},
|
| 3134 |
+
{
|
| 3135 |
+
"update": 1745,
|
| 3136 |
+
"global_step": 7147520,
|
| 3137 |
+
"num_episodes": 2386,
|
| 3138 |
+
"mean_reward": 721.5674746751786,
|
| 3139 |
+
"mean_length": 4056.06,
|
| 3140 |
+
"loss": 62.10371398925781,
|
| 3141 |
+
"sps": 320.26559324554347
|
| 3142 |
+
},
|
| 3143 |
+
{
|
| 3144 |
+
"update": 1750,
|
| 3145 |
+
"global_step": 7168000,
|
| 3146 |
+
"num_episodes": 2388,
|
| 3147 |
+
"mean_reward": 722.019714179039,
|
| 3148 |
+
"mean_length": 4119.0,
|
| 3149 |
+
"loss": 154.1345977783203,
|
| 3150 |
+
"sps": 490.86442866974096
|
| 3151 |
+
},
|
| 3152 |
+
{
|
| 3153 |
+
"update": 1755,
|
| 3154 |
+
"global_step": 7188480,
|
| 3155 |
+
"num_episodes": 2393,
|
| 3156 |
+
"mean_reward": 641.6925968694687,
|
| 3157 |
+
"mean_length": 4085.19,
|
| 3158 |
+
"loss": 3164.498779296875,
|
| 3159 |
+
"sps": 258.3838207181636
|
| 3160 |
+
},
|
| 3161 |
+
{
|
| 3162 |
+
"update": 1760,
|
| 3163 |
+
"global_step": 7208960,
|
| 3164 |
+
"num_episodes": 2395,
|
| 3165 |
+
"mean_reward": 686.4729778194428,
|
| 3166 |
+
"mean_length": 4253.36,
|
| 3167 |
+
"loss": 425.0414733886719,
|
| 3168 |
+
"sps": 362.7607269459368
|
| 3169 |
+
},
|
| 3170 |
+
{
|
| 3171 |
+
"update": 1765,
|
| 3172 |
+
"global_step": 7229440,
|
| 3173 |
+
"num_episodes": 2398,
|
| 3174 |
+
"mean_reward": 781.3392351341248,
|
| 3175 |
+
"mean_length": 4537.14,
|
| 3176 |
+
"loss": 31.12351417541504,
|
| 3177 |
+
"sps": 385.67594003613885
|
| 3178 |
+
},
|
| 3179 |
+
{
|
| 3180 |
+
"update": 1770,
|
| 3181 |
+
"global_step": 7249920,
|
| 3182 |
+
"num_episodes": 2401,
|
| 3183 |
+
"mean_reward": 780.9093813705445,
|
| 3184 |
+
"mean_length": 4438.34,
|
| 3185 |
+
"loss": 154.23956298828125,
|
| 3186 |
+
"sps": 350.9404403984712
|
| 3187 |
+
},
|
| 3188 |
+
{
|
| 3189 |
+
"update": 1775,
|
| 3190 |
+
"global_step": 7270400,
|
| 3191 |
+
"num_episodes": 2409,
|
| 3192 |
+
"mean_reward": 920.4024870014191,
|
| 3193 |
+
"mean_length": 4671.4,
|
| 3194 |
+
"loss": 68.82001495361328,
|
| 3195 |
+
"sps": 373.0457413366687
|
| 3196 |
+
},
|
| 3197 |
+
{
|
| 3198 |
+
"update": 1780,
|
| 3199 |
+
"global_step": 7290880,
|
| 3200 |
+
"num_episodes": 2431,
|
| 3201 |
+
"mean_reward": 661.6825140190125,
|
| 3202 |
+
"mean_length": 4178.67,
|
| 3203 |
+
"loss": 1634.844482421875,
|
| 3204 |
+
"sps": 334.82655519105265
|
| 3205 |
+
},
|
| 3206 |
+
{
|
| 3207 |
+
"update": 1785,
|
| 3208 |
+
"global_step": 7311360,
|
| 3209 |
+
"num_episodes": 2436,
|
| 3210 |
+
"mean_reward": 703.8663965082169,
|
| 3211 |
+
"mean_length": 4154.8,
|
| 3212 |
+
"loss": 36.222721099853516,
|
| 3213 |
+
"sps": 690.9562224821975
|
| 3214 |
+
},
|
| 3215 |
+
{
|
| 3216 |
+
"update": 1790,
|
| 3217 |
+
"global_step": 7331840,
|
| 3218 |
+
"num_episodes": 2442,
|
| 3219 |
+
"mean_reward": 682.8625202751159,
|
| 3220 |
+
"mean_length": 3792.16,
|
| 3221 |
+
"loss": 7.088906288146973,
|
| 3222 |
+
"sps": 546.4602476565249
|
| 3223 |
+
},
|
| 3224 |
+
{
|
| 3225 |
+
"update": 1795,
|
| 3226 |
+
"global_step": 7352320,
|
| 3227 |
+
"num_episodes": 2452,
|
| 3228 |
+
"mean_reward": 668.2820160484314,
|
| 3229 |
+
"mean_length": 3464.88,
|
| 3230 |
+
"loss": 15.93359375,
|
| 3231 |
+
"sps": 338.3906013362985
|
| 3232 |
+
},
|
| 3233 |
+
{
|
| 3234 |
+
"update": 1800,
|
| 3235 |
+
"global_step": 7372800,
|
| 3236 |
+
"num_episodes": 2479,
|
| 3237 |
+
"mean_reward": 503.18441142082213,
|
| 3238 |
+
"mean_length": 2745.39,
|
| 3239 |
+
"loss": 4.317780494689941,
|
| 3240 |
+
"sps": 247.07750153960802
|
| 3241 |
+
},
|
| 3242 |
+
{
|
| 3243 |
+
"update": 1805,
|
| 3244 |
+
"global_step": 7393280,
|
| 3245 |
+
"num_episodes": 2499,
|
| 3246 |
+
"mean_reward": 254.19922243118287,
|
| 3247 |
+
"mean_length": 1727.29,
|
| 3248 |
+
"loss": 2.4029455184936523,
|
| 3249 |
+
"sps": 343.1557628026188
|
| 3250 |
+
},
|
| 3251 |
+
{
|
| 3252 |
+
"update": 1810,
|
| 3253 |
+
"global_step": 7413760,
|
| 3254 |
+
"num_episodes": 2505,
|
| 3255 |
+
"mean_reward": 156.29735308647156,
|
| 3256 |
+
"mean_length": 1608.82,
|
| 3257 |
+
"loss": 50.26245880126953,
|
| 3258 |
+
"sps": 545.8711155437793
|
| 3259 |
+
},
|
| 3260 |
+
{
|
| 3261 |
+
"update": 1815,
|
| 3262 |
+
"global_step": 7434240,
|
| 3263 |
+
"num_episodes": 2511,
|
| 3264 |
+
"mean_reward": 86.22271653652192,
|
| 3265 |
+
"mean_length": 1490.02,
|
| 3266 |
+
"loss": 0.49680042266845703,
|
| 3267 |
+
"sps": 765.2176779813885
|
| 3268 |
+
},
|
| 3269 |
+
{
|
| 3270 |
+
"update": 1820,
|
| 3271 |
+
"global_step": 7454720,
|
| 3272 |
+
"num_episodes": 2517,
|
| 3273 |
+
"mean_reward": 87.76825302124024,
|
| 3274 |
+
"mean_length": 1667.16,
|
| 3275 |
+
"loss": 0.9337818622589111,
|
| 3276 |
+
"sps": 741.1448982958542
|
| 3277 |
+
},
|
| 3278 |
+
{
|
| 3279 |
+
"update": 1825,
|
| 3280 |
+
"global_step": 7475200,
|
| 3281 |
+
"num_episodes": 2525,
|
| 3282 |
+
"mean_reward": 83.8934311246872,
|
| 3283 |
+
"mean_length": 1771.63,
|
| 3284 |
+
"loss": 1.8736273050308228,
|
| 3285 |
+
"sps": 346.82608481484516
|
| 3286 |
+
},
|
| 3287 |
+
{
|
| 3288 |
+
"update": 1830,
|
| 3289 |
+
"global_step": 7495680,
|
| 3290 |
+
"num_episodes": 2536,
|
| 3291 |
+
"mean_reward": 42.52432149887085,
|
| 3292 |
+
"mean_length": 1779.55,
|
| 3293 |
+
"loss": 43.508872985839844,
|
| 3294 |
+
"sps": 538.257412633311
|
| 3295 |
+
},
|
| 3296 |
+
{
|
| 3297 |
+
"update": 1835,
|
| 3298 |
+
"global_step": 7516160,
|
| 3299 |
+
"num_episodes": 2559,
|
| 3300 |
+
"mean_reward": 22.3750723361969,
|
| 3301 |
+
"mean_length": 1585.34,
|
| 3302 |
+
"loss": 11.682701110839844,
|
| 3303 |
+
"sps": 283.17378891804617
|
| 3304 |
+
},
|
| 3305 |
+
{
|
| 3306 |
+
"update": 1840,
|
| 3307 |
+
"global_step": 7536640,
|
| 3308 |
+
"num_episodes": 2572,
|
| 3309 |
+
"mean_reward": 23.224842309951782,
|
| 3310 |
+
"mean_length": 1714.64,
|
| 3311 |
+
"loss": 0.64460289478302,
|
| 3312 |
+
"sps": 945.2402518055575
|
| 3313 |
+
},
|
| 3314 |
+
{
|
| 3315 |
+
"update": 1845,
|
| 3316 |
+
"global_step": 7557120,
|
| 3317 |
+
"num_episodes": 2575,
|
| 3318 |
+
"mean_reward": 23.735417137145998,
|
| 3319 |
+
"mean_length": 1716.6,
|
| 3320 |
+
"loss": 1.5831042528152466,
|
| 3321 |
+
"sps": 1337.9087240256438
|
| 3322 |
+
},
|
| 3323 |
+
{
|
| 3324 |
+
"update": 1850,
|
| 3325 |
+
"global_step": 7577600,
|
| 3326 |
+
"num_episodes": 2575,
|
| 3327 |
+
"mean_reward": 23.735417137145998,
|
| 3328 |
+
"mean_length": 1716.6,
|
| 3329 |
+
"loss": 0.5824832320213318,
|
| 3330 |
+
"sps": 1306.8006548657663
|
| 3331 |
+
},
|
| 3332 |
+
{
|
| 3333 |
+
"update": 1855,
|
| 3334 |
+
"global_step": 7598080,
|
| 3335 |
+
"num_episodes": 2579,
|
| 3336 |
+
"mean_reward": 25.101176109313965,
|
| 3337 |
+
"mean_length": 2001.32,
|
| 3338 |
+
"loss": 3.1498076915740967,
|
| 3339 |
+
"sps": 383.12937784399907
|
| 3340 |
+
},
|
| 3341 |
+
{
|
| 3342 |
+
"update": 1860,
|
| 3343 |
+
"global_step": 7618560,
|
| 3344 |
+
"num_episodes": 2607,
|
| 3345 |
+
"mean_reward": 27.537090787887575,
|
| 3346 |
+
"mean_length": 2252.34,
|
| 3347 |
+
"loss": 2.7028920650482178,
|
| 3348 |
+
"sps": 276.49082168209895
|
| 3349 |
+
},
|
| 3350 |
+
{
|
| 3351 |
+
"update": 1865,
|
| 3352 |
+
"global_step": 7639040,
|
| 3353 |
+
"num_episodes": 2609,
|
| 3354 |
+
"mean_reward": 27.678814001083374,
|
| 3355 |
+
"mean_length": 2266.75,
|
| 3356 |
+
"loss": 1.0194354057312012,
|
| 3357 |
+
"sps": 829.6019480631423
|
| 3358 |
+
},
|
| 3359 |
+
{
|
| 3360 |
+
"update": 1870,
|
| 3361 |
+
"global_step": 7659520,
|
| 3362 |
+
"num_episodes": 2609,
|
| 3363 |
+
"mean_reward": 27.678814001083374,
|
| 3364 |
+
"mean_length": 2266.75,
|
| 3365 |
+
"loss": 0.69590824842453,
|
| 3366 |
+
"sps": 1339.889941319705
|
| 3367 |
+
},
|
| 3368 |
+
{
|
| 3369 |
+
"update": 1875,
|
| 3370 |
+
"global_step": 7680000,
|
| 3371 |
+
"num_episodes": 2610,
|
| 3372 |
+
"mean_reward": 27.743932600021363,
|
| 3373 |
+
"mean_length": 2363.84,
|
| 3374 |
+
"loss": 4.22328519821167,
|
| 3375 |
+
"sps": 1047.687217978352
|
| 3376 |
+
},
|
| 3377 |
+
{
|
| 3378 |
+
"update": 1880,
|
| 3379 |
+
"global_step": 7700480,
|
| 3380 |
+
"num_episodes": 2623,
|
| 3381 |
+
"mean_reward": 28.715706405639647,
|
| 3382 |
+
"mean_length": 2373.15,
|
| 3383 |
+
"loss": 15.052788734436035,
|
| 3384 |
+
"sps": 180.92434386649956
|
| 3385 |
+
},
|
| 3386 |
+
{
|
| 3387 |
+
"update": 1885,
|
| 3388 |
+
"global_step": 7720960,
|
| 3389 |
+
"num_episodes": 2650,
|
| 3390 |
+
"mean_reward": 28.79868775844574,
|
| 3391 |
+
"mean_length": 2376.77,
|
| 3392 |
+
"loss": 141.97862243652344,
|
| 3393 |
+
"sps": 189.85363801957897
|
| 3394 |
+
},
|
| 3395 |
+
{
|
| 3396 |
+
"update": 1890,
|
| 3397 |
+
"global_step": 7741440,
|
| 3398 |
+
"num_episodes": 2663,
|
| 3399 |
+
"mean_reward": 29.01506271839142,
|
| 3400 |
+
"mean_length": 2187.12,
|
| 3401 |
+
"loss": 2.7120704650878906,
|
| 3402 |
+
"sps": 442.6728082704278
|
| 3403 |
+
},
|
| 3404 |
+
{
|
| 3405 |
+
"update": 1895,
|
| 3406 |
+
"global_step": 7761920,
|
| 3407 |
+
"num_episodes": 2664,
|
| 3408 |
+
"mean_reward": 28.84576090812683,
|
| 3409 |
+
"mean_length": 2212.69,
|
| 3410 |
+
"loss": 0.6469894647598267,
|
| 3411 |
+
"sps": 1603.7569257295258
|
| 3412 |
+
},
|
| 3413 |
+
{
|
| 3414 |
+
"update": 1900,
|
| 3415 |
+
"global_step": 7782400,
|
| 3416 |
+
"num_episodes": 2665,
|
| 3417 |
+
"mean_reward": 29.100953969955444,
|
| 3418 |
+
"mean_length": 2212.69,
|
| 3419 |
+
"loss": 5.927608489990234,
|
| 3420 |
+
"sps": 1560.5345956258918
|
| 3421 |
+
},
|
| 3422 |
+
{
|
| 3423 |
+
"update": 1905,
|
| 3424 |
+
"global_step": 7802880,
|
| 3425 |
+
"num_episodes": 2677,
|
| 3426 |
+
"mean_reward": 29.594479999542237,
|
| 3427 |
+
"mean_length": 2279.92,
|
| 3428 |
+
"loss": 3.0546085834503174,
|
| 3429 |
+
"sps": 239.632742367245
|
| 3430 |
+
},
|
| 3431 |
+
{
|
| 3432 |
+
"update": 1910,
|
| 3433 |
+
"global_step": 7823360,
|
| 3434 |
+
"num_episodes": 2696,
|
| 3435 |
+
"mean_reward": 29.67495318889618,
|
| 3436 |
+
"mean_length": 2013.09,
|
| 3437 |
+
"loss": 0.40485668182373047,
|
| 3438 |
+
"sps": 483.9873532409158
|
| 3439 |
+
},
|
| 3440 |
+
{
|
| 3441 |
+
"update": 1915,
|
| 3442 |
+
"global_step": 7843840,
|
| 3443 |
+
"num_episodes": 2706,
|
| 3444 |
+
"mean_reward": 30.284353771209716,
|
| 3445 |
+
"mean_length": 2114.96,
|
| 3446 |
+
"loss": 1.9687494039535522,
|
| 3447 |
+
"sps": 668.5066115534931
|
| 3448 |
+
},
|
| 3449 |
+
{
|
| 3450 |
+
"update": 1920,
|
| 3451 |
+
"global_step": 7864320,
|
| 3452 |
+
"num_episodes": 2713,
|
| 3453 |
+
"mean_reward": 28.00047863960266,
|
| 3454 |
+
"mean_length": 1718.87,
|
| 3455 |
+
"loss": 0.2566870450973511,
|
| 3456 |
+
"sps": 774.1152448288775
|
| 3457 |
+
},
|
| 3458 |
+
{
|
| 3459 |
+
"update": 1925,
|
| 3460 |
+
"global_step": 7884800,
|
| 3461 |
+
"num_episodes": 2728,
|
| 3462 |
+
"mean_reward": 28.49471785068512,
|
| 3463 |
+
"mean_length": 1709.19,
|
| 3464 |
+
"loss": 0.5462437272071838,
|
| 3465 |
+
"sps": 335.32752289720815
|
| 3466 |
+
},
|
| 3467 |
+
{
|
| 3468 |
+
"update": 1930,
|
| 3469 |
+
"global_step": 7905280,
|
| 3470 |
+
"num_episodes": 2749,
|
| 3471 |
+
"mean_reward": 29.774335384368896,
|
| 3472 |
+
"mean_length": 1793.46,
|
| 3473 |
+
"loss": 1.6195909976959229,
|
| 3474 |
+
"sps": 151.6658643145884
|
| 3475 |
+
},
|
| 3476 |
+
{
|
| 3477 |
+
"update": 1935,
|
| 3478 |
+
"global_step": 7925760,
|
| 3479 |
+
"num_episodes": 2763,
|
| 3480 |
+
"mean_reward": 29.902848501205444,
|
| 3481 |
+
"mean_length": 1903.12,
|
| 3482 |
+
"loss": 3.346653461456299,
|
| 3483 |
+
"sps": 299.9200663991073
|
| 3484 |
+
},
|
| 3485 |
+
{
|
| 3486 |
+
"update": 1940,
|
| 3487 |
+
"global_step": 7946240,
|
| 3488 |
+
"num_episodes": 2766,
|
| 3489 |
+
"mean_reward": 29.951358599662782,
|
| 3490 |
+
"mean_length": 1817.08,
|
| 3491 |
+
"loss": 2.196648120880127,
|
| 3492 |
+
"sps": 612.8349441003236
|
| 3493 |
+
},
|
| 3494 |
+
{
|
| 3495 |
+
"update": 1945,
|
| 3496 |
+
"global_step": 7966720,
|
| 3497 |
+
"num_episodes": 2775,
|
| 3498 |
+
"mean_reward": 27.90867582321167,
|
| 3499 |
+
"mean_length": 1530.25,
|
| 3500 |
+
"loss": 5.727337837219238,
|
| 3501 |
+
"sps": 686.4829120395315
|
| 3502 |
+
},
|
| 3503 |
+
{
|
| 3504 |
+
"update": 1950,
|
| 3505 |
+
"global_step": 7987200,
|
| 3506 |
+
"num_episodes": 2791,
|
| 3507 |
+
"mean_reward": 27.395657448768617,
|
| 3508 |
+
"mean_length": 1515.36,
|
| 3509 |
+
"loss": 0.2642287015914917,
|
| 3510 |
+
"sps": 427.4124315071339
|
| 3511 |
+
},
|
| 3512 |
+
{
|
| 3513 |
+
"update": 1955,
|
| 3514 |
+
"global_step": 8007680,
|
| 3515 |
+
"num_episodes": 2811,
|
| 3516 |
+
"mean_reward": 29.46188481807709,
|
| 3517 |
+
"mean_length": 1804.43,
|
| 3518 |
+
"loss": 1.1504522562026978,
|
| 3519 |
+
"sps": 440.35140268496957
|
| 3520 |
+
},
|
| 3521 |
+
{
|
| 3522 |
+
"update": 1960,
|
| 3523 |
+
"global_step": 8028160,
|
| 3524 |
+
"num_episodes": 2811,
|
| 3525 |
+
"mean_reward": 29.46188481807709,
|
| 3526 |
+
"mean_length": 1804.43,
|
| 3527 |
+
"loss": 0.6443239450454712,
|
| 3528 |
+
"sps": 897.6638295466576
|
| 3529 |
+
},
|
| 3530 |
+
{
|
| 3531 |
+
"update": 1965,
|
| 3532 |
+
"global_step": 8048640,
|
| 3533 |
+
"num_episodes": 2811,
|
| 3534 |
+
"mean_reward": 29.46188481807709,
|
| 3535 |
+
"mean_length": 1804.43,
|
| 3536 |
+
"loss": 0.9464260339736938,
|
| 3537 |
+
"sps": 1231.9540613883512
|
| 3538 |
+
},
|
| 3539 |
+
{
|
| 3540 |
+
"update": 1970,
|
| 3541 |
+
"global_step": 8069120,
|
| 3542 |
+
"num_episodes": 2816,
|
| 3543 |
+
"mean_reward": 30.10758180618286,
|
| 3544 |
+
"mean_length": 1900.22,
|
| 3545 |
+
"loss": 13.55959701538086,
|
| 3546 |
+
"sps": 762.2875965279533
|
| 3547 |
+
},
|
| 3548 |
+
{
|
| 3549 |
+
"update": 1975,
|
| 3550 |
+
"global_step": 8089600,
|
| 3551 |
+
"num_episodes": 2836,
|
| 3552 |
+
"mean_reward": 33.175699801445006,
|
| 3553 |
+
"mean_length": 2303.58,
|
| 3554 |
+
"loss": 7.275441646575928,
|
| 3555 |
+
"sps": 227.75311612847298
|
| 3556 |
+
},
|
| 3557 |
+
{
|
| 3558 |
+
"update": 1980,
|
| 3559 |
+
"global_step": 8110080,
|
| 3560 |
+
"num_episodes": 2856,
|
| 3561 |
+
"mean_reward": 29.203288111686707,
|
| 3562 |
+
"mean_length": 2029.45,
|
| 3563 |
+
"loss": 39.95777130126953,
|
| 3564 |
+
"sps": 325.31625618278383
|
| 3565 |
+
},
|
| 3566 |
+
{
|
| 3567 |
+
"update": 1985,
|
| 3568 |
+
"global_step": 8130560,
|
| 3569 |
+
"num_episodes": 2877,
|
| 3570 |
+
"mean_reward": 26.940120091438292,
|
| 3571 |
+
"mean_length": 1738.19,
|
| 3572 |
+
"loss": 2.9013671875,
|
| 3573 |
+
"sps": 477.60825044232615
|
| 3574 |
+
},
|
| 3575 |
+
{
|
| 3576 |
+
"update": 1990,
|
| 3577 |
+
"global_step": 8151040,
|
| 3578 |
+
"num_episodes": 2881,
|
| 3579 |
+
"mean_reward": 26.892020201683046,
|
| 3580 |
+
"mean_length": 1748.27,
|
| 3581 |
+
"loss": 1.5360685586929321,
|
| 3582 |
+
"sps": 779.3787507434323
|
| 3583 |
+
},
|
| 3584 |
+
{
|
| 3585 |
+
"update": 1995,
|
| 3586 |
+
"global_step": 8171520,
|
| 3587 |
+
"num_episodes": 2887,
|
| 3588 |
+
"mean_reward": 28.383681316375732,
|
| 3589 |
+
"mean_length": 2035.38,
|
| 3590 |
+
"loss": 0.28828829526901245,
|
| 3591 |
+
"sps": 528.7312594886902
|
| 3592 |
+
},
|
| 3593 |
+
{
|
| 3594 |
+
"update": 2000,
|
| 3595 |
+
"global_step": 8192000,
|
| 3596 |
+
"num_episodes": 2894,
|
| 3597 |
+
"mean_reward": 27.269041929244995,
|
| 3598 |
+
"mean_length": 2017.08,
|
| 3599 |
+
"loss": 92.5503158569336,
|
| 3600 |
+
"sps": 423.8490051832835
|
| 3601 |
+
},
|
| 3602 |
+
{
|
| 3603 |
+
"update": 2005,
|
| 3604 |
+
"global_step": 8212480,
|
| 3605 |
+
"num_episodes": 2910,
|
| 3606 |
+
"mean_reward": 29.26204339504242,
|
| 3607 |
+
"mean_length": 2043.4,
|
| 3608 |
+
"loss": 1.737417221069336,
|
| 3609 |
+
"sps": 319.480134990497
|
| 3610 |
+
},
|
| 3611 |
+
{
|
| 3612 |
+
"update": 2010,
|
| 3613 |
+
"global_step": 8232960,
|
| 3614 |
+
"num_episodes": 2914,
|
| 3615 |
+
"mean_reward": 27.918287878036498,
|
| 3616 |
+
"mean_length": 1848.0,
|
| 3617 |
+
"loss": 9.918323516845703,
|
| 3618 |
+
"sps": 520.2825326468419
|
| 3619 |
+
},
|
| 3620 |
+
{
|
| 3621 |
+
"update": 2015,
|
| 3622 |
+
"global_step": 8253440,
|
| 3623 |
+
"num_episodes": 2923,
|
| 3624 |
+
"mean_reward": 25.578041405677794,
|
| 3625 |
+
"mean_length": 1641.01,
|
| 3626 |
+
"loss": 101.00448608398438,
|
| 3627 |
+
"sps": 412.83971034964594
|
| 3628 |
+
},
|
| 3629 |
+
{
|
| 3630 |
+
"update": 2020,
|
| 3631 |
+
"global_step": 8273920,
|
| 3632 |
+
"num_episodes": 2929,
|
| 3633 |
+
"mean_reward": 24.985388655662536,
|
| 3634 |
+
"mean_length": 1728.38,
|
| 3635 |
+
"loss": 33.80594253540039,
|
| 3636 |
+
"sps": 407.32375547775194
|
| 3637 |
+
},
|
| 3638 |
+
{
|
| 3639 |
+
"update": 2025,
|
| 3640 |
+
"global_step": 8294400,
|
| 3641 |
+
"num_episodes": 2941,
|
| 3642 |
+
"mean_reward": 54.48088625907898,
|
| 3643 |
+
"mean_length": 1727.06,
|
| 3644 |
+
"loss": 57.52255630493164,
|
| 3645 |
+
"sps": 251.07848653412563
|
| 3646 |
+
},
|
| 3647 |
+
{
|
| 3648 |
+
"update": 2030,
|
| 3649 |
+
"global_step": 8314880,
|
| 3650 |
+
"num_episodes": 2952,
|
| 3651 |
+
"mean_reward": 62.7720309972763,
|
| 3652 |
+
"mean_length": 1877.51,
|
| 3653 |
+
"loss": 18.3802547454834,
|
| 3654 |
+
"sps": 355.5720033718748
|
| 3655 |
+
},
|
| 3656 |
+
{
|
| 3657 |
+
"update": 2035,
|
| 3658 |
+
"global_step": 8335360,
|
| 3659 |
+
"num_episodes": 2957,
|
| 3660 |
+
"mean_reward": 62.98542010307312,
|
| 3661 |
+
"mean_length": 1979.5,
|
| 3662 |
+
"loss": 1.3044229745864868,
|
| 3663 |
+
"sps": 646.2262220511143
|
| 3664 |
+
},
|
| 3665 |
+
{
|
| 3666 |
+
"update": 2040,
|
| 3667 |
+
"global_step": 8355840,
|
| 3668 |
+
"num_episodes": 2961,
|
| 3669 |
+
"mean_reward": 63.64336392879486,
|
| 3670 |
+
"mean_length": 2180.16,
|
| 3671 |
+
"loss": 92.43401336669922,
|
| 3672 |
+
"sps": 659.5681486510539
|
| 3673 |
+
},
|
| 3674 |
+
{
|
| 3675 |
+
"update": 2045,
|
| 3676 |
+
"global_step": 8376320,
|
| 3677 |
+
"num_episodes": 2962,
|
| 3678 |
+
"mean_reward": 63.40275900363922,
|
| 3679 |
+
"mean_length": 2203.23,
|
| 3680 |
+
"loss": 1.014630675315857,
|
| 3681 |
+
"sps": 1446.1879050125103
|
| 3682 |
+
},
|
| 3683 |
+
{
|
| 3684 |
+
"update": 2050,
|
| 3685 |
+
"global_step": 8396800,
|
| 3686 |
+
"num_episodes": 2986,
|
| 3687 |
+
"mean_reward": 79.26061116695404,
|
| 3688 |
+
"mean_length": 2214.81,
|
| 3689 |
+
"loss": 29.98980712890625,
|
| 3690 |
+
"sps": 205.60997792847448
|
| 3691 |
+
},
|
| 3692 |
+
{
|
| 3693 |
+
"update": 2055,
|
| 3694 |
+
"global_step": 8417280,
|
| 3695 |
+
"num_episodes": 3001,
|
| 3696 |
+
"mean_reward": 82.85091641426087,
|
| 3697 |
+
"mean_length": 2227.86,
|
| 3698 |
+
"loss": 32.844966888427734,
|
| 3699 |
+
"sps": 159.2487235394598
|
| 3700 |
+
},
|
| 3701 |
+
{
|
| 3702 |
+
"update": 2060,
|
| 3703 |
+
"global_step": 8437760,
|
| 3704 |
+
"num_episodes": 3027,
|
| 3705 |
+
"mean_reward": 78.89424407482147,
|
| 3706 |
+
"mean_length": 1849.23,
|
| 3707 |
+
"loss": 103.22246551513672,
|
| 3708 |
+
"sps": 213.8993421623802
|
| 3709 |
+
},
|
| 3710 |
+
{
|
| 3711 |
+
"update": 2065,
|
| 3712 |
+
"global_step": 8458240,
|
| 3713 |
+
"num_episodes": 3033,
|
| 3714 |
+
"mean_reward": 78.97739854335785,
|
| 3715 |
+
"mean_length": 1848.21,
|
| 3716 |
+
"loss": 29.219009399414062,
|
| 3717 |
+
"sps": 303.98893287836097
|
| 3718 |
+
},
|
| 3719 |
+
{
|
| 3720 |
+
"update": 2070,
|
| 3721 |
+
"global_step": 8478720,
|
| 3722 |
+
"num_episodes": 3038,
|
| 3723 |
+
"mean_reward": 78.37423317909241,
|
| 3724 |
+
"mean_length": 1807.15,
|
| 3725 |
+
"loss": 34.15611267089844,
|
| 3726 |
+
"sps": 219.78900023670354
|
| 3727 |
+
},
|
| 3728 |
+
{
|
| 3729 |
+
"update": 2075,
|
| 3730 |
+
"global_step": 8499200,
|
| 3731 |
+
"num_episodes": 3052,
|
| 3732 |
+
"mean_reward": 75.33004099369049,
|
| 3733 |
+
"mean_length": 1865.63,
|
| 3734 |
+
"loss": 26.766494750976562,
|
| 3735 |
+
"sps": 339.7451627672537
|
| 3736 |
+
},
|
| 3737 |
+
{
|
| 3738 |
+
"update": 2080,
|
| 3739 |
+
"global_step": 8519680,
|
| 3740 |
+
"num_episodes": 3056,
|
| 3741 |
+
"mean_reward": 75.64053434848785,
|
| 3742 |
+
"mean_length": 1968.04,
|
| 3743 |
+
"loss": 176.32748413085938,
|
| 3744 |
+
"sps": 334.0194819221175
|
| 3745 |
+
},
|
| 3746 |
+
{
|
| 3747 |
+
"update": 2085,
|
| 3748 |
+
"global_step": 8540160,
|
| 3749 |
+
"num_episodes": 3066,
|
| 3750 |
+
"mean_reward": 74.47905586719513,
|
| 3751 |
+
"mean_length": 1544.14,
|
| 3752 |
+
"loss": 167.32608032226562,
|
| 3753 |
+
"sps": 393.50550599249544
|
| 3754 |
+
},
|
| 3755 |
+
{
|
| 3756 |
+
"update": 2090,
|
| 3757 |
+
"global_step": 8560640,
|
| 3758 |
+
"num_episodes": 3072,
|
| 3759 |
+
"mean_reward": 75.01324489593506,
|
| 3760 |
+
"mean_length": 1620.95,
|
| 3761 |
+
"loss": 40.1760139465332,
|
| 3762 |
+
"sps": 272.5369799883836
|
| 3763 |
+
},
|
| 3764 |
+
{
|
| 3765 |
+
"update": 2095,
|
| 3766 |
+
"global_step": 8581120,
|
| 3767 |
+
"num_episodes": 3084,
|
| 3768 |
+
"mean_reward": 80.59875289440156,
|
| 3769 |
+
"mean_length": 1815.35,
|
| 3770 |
+
"loss": 23.691143035888672,
|
| 3771 |
+
"sps": 460.4555876617225
|
| 3772 |
+
},
|
| 3773 |
+
{
|
| 3774 |
+
"update": 2100,
|
| 3775 |
+
"global_step": 8601600,
|
| 3776 |
+
"num_episodes": 3092,
|
| 3777 |
+
"mean_reward": 151.1377474308014,
|
| 3778 |
+
"mean_length": 2023.52,
|
| 3779 |
+
"loss": 119.31157684326172,
|
| 3780 |
+
"sps": 230.98807371797147
|
| 3781 |
+
},
|
| 3782 |
+
{
|
| 3783 |
+
"update": 2105,
|
| 3784 |
+
"global_step": 8622080,
|
| 3785 |
+
"num_episodes": 3104,
|
| 3786 |
+
"mean_reward": 145.0986036682129,
|
| 3787 |
+
"mean_length": 1964.44,
|
| 3788 |
+
"loss": 17.907983779907227,
|
| 3789 |
+
"sps": 136.7176138415176
|
| 3790 |
+
},
|
| 3791 |
+
{
|
| 3792 |
+
"update": 2110,
|
| 3793 |
+
"global_step": 8642560,
|
| 3794 |
+
"num_episodes": 3113,
|
| 3795 |
+
"mean_reward": 145.05979912757874,
|
| 3796 |
+
"mean_length": 2015.23,
|
| 3797 |
+
"loss": 238.5266876220703,
|
| 3798 |
+
"sps": 191.61578614248398
|
| 3799 |
+
},
|
| 3800 |
+
{
|
| 3801 |
+
"update": 2115,
|
| 3802 |
+
"global_step": 8663040,
|
| 3803 |
+
"num_episodes": 3127,
|
| 3804 |
+
"mean_reward": 145.9841158914566,
|
| 3805 |
+
"mean_length": 2223.16,
|
| 3806 |
+
"loss": 279.5526428222656,
|
| 3807 |
+
"sps": 178.22145258830818
|
| 3808 |
+
},
|
| 3809 |
+
{
|
| 3810 |
+
"update": 2120,
|
| 3811 |
+
"global_step": 8683520,
|
| 3812 |
+
"num_episodes": 3129,
|
| 3813 |
+
"mean_reward": 161.8294042444229,
|
| 3814 |
+
"mean_length": 2317.37,
|
| 3815 |
+
"loss": 4402.13232421875,
|
| 3816 |
+
"sps": 187.96868067815723
|
| 3817 |
+
},
|
| 3818 |
+
{
|
| 3819 |
+
"update": 2125,
|
| 3820 |
+
"global_step": 8704000,
|
| 3821 |
+
"num_episodes": 3131,
|
| 3822 |
+
"mean_reward": 254.4432011270523,
|
| 3823 |
+
"mean_length": 2415.71,
|
| 3824 |
+
"loss": 253.15243530273438,
|
| 3825 |
+
"sps": 389.3006404112279
|
| 3826 |
+
},
|
| 3827 |
+
{
|
| 3828 |
+
"update": 2130,
|
| 3829 |
+
"global_step": 8724480,
|
| 3830 |
+
"num_episodes": 3136,
|
| 3831 |
+
"mean_reward": 308.86108244895934,
|
| 3832 |
+
"mean_length": 2455.38,
|
| 3833 |
+
"loss": 42.87656784057617,
|
| 3834 |
+
"sps": 289.06916804822475
|
| 3835 |
+
},
|
| 3836 |
+
{
|
| 3837 |
+
"update": 2135,
|
| 3838 |
+
"global_step": 8744960,
|
| 3839 |
+
"num_episodes": 3151,
|
| 3840 |
+
"mean_reward": 442.90291794776914,
|
| 3841 |
+
"mean_length": 2544.55,
|
| 3842 |
+
"loss": 52.280975341796875,
|
| 3843 |
+
"sps": 168.18531939110147
|
| 3844 |
+
},
|
| 3845 |
+
{
|
| 3846 |
+
"update": 2140,
|
| 3847 |
+
"global_step": 8765440,
|
| 3848 |
+
"num_episodes": 3153,
|
| 3849 |
+
"mean_reward": 443.3635806703567,
|
| 3850 |
+
"mean_length": 2596.27,
|
| 3851 |
+
"loss": 123.76752471923828,
|
| 3852 |
+
"sps": 250.64368624913917
|
| 3853 |
+
},
|
| 3854 |
+
{
|
| 3855 |
+
"update": 2145,
|
| 3856 |
+
"global_step": 8785920,
|
| 3857 |
+
"num_episodes": 3154,
|
| 3858 |
+
"mean_reward": 443.81920017719267,
|
| 3859 |
+
"mean_length": 2693.35,
|
| 3860 |
+
"loss": 8.35338020324707,
|
| 3861 |
+
"sps": 403.9011407049708
|
| 3862 |
+
},
|
| 3863 |
+
{
|
| 3864 |
+
"update": 2150,
|
| 3865 |
+
"global_step": 8806400,
|
| 3866 |
+
"num_episodes": 3158,
|
| 3867 |
+
"mean_reward": 578.3950145959855,
|
| 3868 |
+
"mean_length": 2690.97,
|
| 3869 |
+
"loss": 117.6234359741211,
|
| 3870 |
+
"sps": 427.3976727795614
|
| 3871 |
+
},
|
| 3872 |
+
{
|
| 3873 |
+
"update": 2155,
|
| 3874 |
+
"global_step": 8826880,
|
| 3875 |
+
"num_episodes": 3168,
|
| 3876 |
+
"mean_reward": 593.7985137224198,
|
| 3877 |
+
"mean_length": 2964.72,
|
| 3878 |
+
"loss": 27.907575607299805,
|
| 3879 |
+
"sps": 408.92434877647025
|
| 3880 |
+
},
|
| 3881 |
+
{
|
| 3882 |
+
"update": 2160,
|
| 3883 |
+
"global_step": 8847360,
|
| 3884 |
+
"num_episodes": 3176,
|
| 3885 |
+
"mean_reward": 696.11108481884,
|
| 3886 |
+
"mean_length": 2789.14,
|
| 3887 |
+
"loss": 37.44743347167969,
|
| 3888 |
+
"sps": 405.43106143344477
|
| 3889 |
+
},
|
| 3890 |
+
{
|
| 3891 |
+
"update": 2165,
|
| 3892 |
+
"global_step": 8867840,
|
| 3893 |
+
"num_episodes": 3181,
|
| 3894 |
+
"mean_reward": 691.3086440181733,
|
| 3895 |
+
"mean_length": 2841.13,
|
| 3896 |
+
"loss": 444.12481689453125,
|
| 3897 |
+
"sps": 410.99575565900966
|
| 3898 |
+
},
|
| 3899 |
+
{
|
| 3900 |
+
"update": 2170,
|
| 3901 |
+
"global_step": 8888320,
|
| 3902 |
+
"num_episodes": 3186,
|
| 3903 |
+
"mean_reward": 696.4550316858291,
|
| 3904 |
+
"mean_length": 2910.25,
|
| 3905 |
+
"loss": 221.63902282714844,
|
| 3906 |
+
"sps": 355.0140974319845
|
| 3907 |
+
},
|
| 3908 |
+
{
|
| 3909 |
+
"update": 2175,
|
| 3910 |
+
"global_step": 8908800,
|
| 3911 |
+
"num_episodes": 3191,
|
| 3912 |
+
"mean_reward": 696.0580731773376,
|
| 3913 |
+
"mean_length": 3004.52,
|
| 3914 |
+
"loss": 762.4512939453125,
|
| 3915 |
+
"sps": 303.24516246589195
|
| 3916 |
+
},
|
| 3917 |
+
{
|
| 3918 |
+
"update": 2180,
|
| 3919 |
+
"global_step": 8929280,
|
| 3920 |
+
"num_episodes": 3197,
|
| 3921 |
+
"mean_reward": 814.6755250024795,
|
| 3922 |
+
"mean_length": 3002.62,
|
| 3923 |
+
"loss": 409.33624267578125,
|
| 3924 |
+
"sps": 427.0124459168339
|
| 3925 |
+
},
|
| 3926 |
+
{
|
| 3927 |
+
"update": 2185,
|
| 3928 |
+
"global_step": 8949760,
|
| 3929 |
+
"num_episodes": 3210,
|
| 3930 |
+
"mean_reward": 934.5317647647857,
|
| 3931 |
+
"mean_length": 3211.49,
|
| 3932 |
+
"loss": 95.55060577392578,
|
| 3933 |
+
"sps": 125.75423605418091
|
| 3934 |
+
},
|
| 3935 |
+
{
|
| 3936 |
+
"update": 2190,
|
| 3937 |
+
"global_step": 8970240,
|
| 3938 |
+
"num_episodes": 3214,
|
| 3939 |
+
"mean_reward": 1002.574015007019,
|
| 3940 |
+
"mean_length": 3132.07,
|
| 3941 |
+
"loss": 68.63960266113281,
|
| 3942 |
+
"sps": 206.72189870239387
|
| 3943 |
+
},
|
| 3944 |
+
{
|
| 3945 |
+
"update": 2195,
|
| 3946 |
+
"global_step": 8990720,
|
| 3947 |
+
"num_episodes": 3225,
|
| 3948 |
+
"mean_reward": 1036.229081878662,
|
| 3949 |
+
"mean_length": 3290.05,
|
| 3950 |
+
"loss": 450.1454772949219,
|
| 3951 |
+
"sps": 308.8153724070321
|
| 3952 |
+
},
|
| 3953 |
+
{
|
| 3954 |
+
"update": 2200,
|
| 3955 |
+
"global_step": 9011200,
|
| 3956 |
+
"num_episodes": 3226,
|
| 3957 |
+
"mean_reward": 1175.8488982009887,
|
| 3958 |
+
"mean_length": 3386.93,
|
| 3959 |
+
"loss": 11.516603469848633,
|
| 3960 |
+
"sps": 505.34211227316496
|
| 3961 |
+
},
|
| 3962 |
+
{
|
| 3963 |
+
"update": 2205,
|
| 3964 |
+
"global_step": 9031680,
|
| 3965 |
+
"num_episodes": 3228,
|
| 3966 |
+
"mean_reward": 1241.2947177028657,
|
| 3967 |
+
"mean_length": 3452.12,
|
| 3968 |
+
"loss": 998.0031127929688,
|
| 3969 |
+
"sps": 380.7435127282772
|
| 3970 |
+
},
|
| 3971 |
+
{
|
| 3972 |
+
"update": 2210,
|
| 3973 |
+
"global_step": 9052160,
|
| 3974 |
+
"num_episodes": 3234,
|
| 3975 |
+
"mean_reward": 1148.464052476883,
|
| 3976 |
+
"mean_length": 3444.2,
|
| 3977 |
+
"loss": 0.2201317399740219,
|
| 3978 |
+
"sps": 447.01108197826755
|
| 3979 |
+
},
|
| 3980 |
+
{
|
| 3981 |
+
"update": 2215,
|
| 3982 |
+
"global_step": 9072640,
|
| 3983 |
+
"num_episodes": 3251,
|
| 3984 |
+
"mean_reward": 983.5756113386154,
|
| 3985 |
+
"mean_length": 3185.62,
|
| 3986 |
+
"loss": 10.140728950500488,
|
| 3987 |
+
"sps": 285.88922550188585
|
| 3988 |
+
},
|
| 3989 |
+
{
|
| 3990 |
+
"update": 2220,
|
| 3991 |
+
"global_step": 9093120,
|
| 3992 |
+
"num_episodes": 3267,
|
| 3993 |
+
"mean_reward": 830.9440940666199,
|
| 3994 |
+
"mean_length": 2711.54,
|
| 3995 |
+
"loss": 23.857481002807617,
|
| 3996 |
+
"sps": 225.0139483384211
|
| 3997 |
+
},
|
| 3998 |
+
{
|
| 3999 |
+
"update": 2225,
|
| 4000 |
+
"global_step": 9113600,
|
| 4001 |
+
"num_episodes": 3285,
|
| 4002 |
+
"mean_reward": 755.7127734375,
|
| 4003 |
+
"mean_length": 2369.97,
|
| 4004 |
+
"loss": 263.3361511230469,
|
| 4005 |
+
"sps": 274.6876121563017
|
| 4006 |
+
},
|
| 4007 |
+
{
|
| 4008 |
+
"update": 2230,
|
| 4009 |
+
"global_step": 9134080,
|
| 4010 |
+
"num_episodes": 3291,
|
| 4011 |
+
"mean_reward": 754.6721585416794,
|
| 4012 |
+
"mean_length": 2306.49,
|
| 4013 |
+
"loss": 4289.046875,
|
| 4014 |
+
"sps": 174.4840112420559
|
| 4015 |
+
},
|
| 4016 |
+
{
|
| 4017 |
+
"update": 2235,
|
| 4018 |
+
"global_step": 9154560,
|
| 4019 |
+
"num_episodes": 3298,
|
| 4020 |
+
"mean_reward": 730.0353905773163,
|
| 4021 |
+
"mean_length": 2354.08,
|
| 4022 |
+
"loss": 84.65528869628906,
|
| 4023 |
+
"sps": 265.5093767251286
|
| 4024 |
+
},
|
| 4025 |
+
{
|
| 4026 |
+
"update": 2240,
|
| 4027 |
+
"global_step": 9175040,
|
| 4028 |
+
"num_episodes": 3300,
|
| 4029 |
+
"mean_reward": 660.2916961956024,
|
| 4030 |
+
"mean_length": 2256.21,
|
| 4031 |
+
"loss": 388.5572814941406,
|
| 4032 |
+
"sps": 407.65937488684284
|
| 4033 |
+
},
|
| 4034 |
+
{
|
| 4035 |
+
"update": 2245,
|
| 4036 |
+
"global_step": 9195520,
|
| 4037 |
+
"num_episodes": 3309,
|
| 4038 |
+
"mean_reward": 687.2124669837951,
|
| 4039 |
+
"mean_length": 2477.43,
|
| 4040 |
+
"loss": 172.86532592773438,
|
| 4041 |
+
"sps": 298.38812190862865
|
| 4042 |
+
},
|
| 4043 |
+
{
|
| 4044 |
+
"update": 2250,
|
| 4045 |
+
"global_step": 9216000,
|
| 4046 |
+
"num_episodes": 3310,
|
| 4047 |
+
"mean_reward": 687.4369230651855,
|
| 4048 |
+
"mean_length": 2481.91,
|
| 4049 |
+
"loss": 14.442253112792969,
|
| 4050 |
+
"sps": 667.1891280431901
|
| 4051 |
+
},
|
| 4052 |
+
{
|
| 4053 |
+
"update": 2255,
|
| 4054 |
+
"global_step": 9236480,
|
| 4055 |
+
"num_episodes": 3320,
|
| 4056 |
+
"mean_reward": 686.6187604236603,
|
| 4057 |
+
"mean_length": 2631.57,
|
| 4058 |
+
"loss": 8.769046783447266,
|
| 4059 |
+
"sps": 248.0906360841076
|
| 4060 |
+
},
|
| 4061 |
+
{
|
| 4062 |
+
"update": 2260,
|
| 4063 |
+
"global_step": 9256960,
|
| 4064 |
+
"num_episodes": 3324,
|
| 4065 |
+
"mean_reward": 714.0761754512787,
|
| 4066 |
+
"mean_length": 2596.79,
|
| 4067 |
+
"loss": 2.7038824558258057,
|
| 4068 |
+
"sps": 611.7833643654915
|
| 4069 |
+
},
|
| 4070 |
+
{
|
| 4071 |
+
"update": 2265,
|
| 4072 |
+
"global_step": 9277440,
|
| 4073 |
+
"num_episodes": 3333,
|
| 4074 |
+
"mean_reward": 514.9936645078659,
|
| 4075 |
+
"mean_length": 2480.39,
|
| 4076 |
+
"loss": 107.10433959960938,
|
| 4077 |
+
"sps": 352.06042337330143
|
| 4078 |
+
},
|
| 4079 |
+
{
|
| 4080 |
+
"update": 2270,
|
| 4081 |
+
"global_step": 9297920,
|
| 4082 |
+
"num_episodes": 3333,
|
| 4083 |
+
"mean_reward": 514.9936645078659,
|
| 4084 |
+
"mean_length": 2480.39,
|
| 4085 |
+
"loss": 205.3878936767578,
|
| 4086 |
+
"sps": 557.4872251219026
|
| 4087 |
+
},
|
| 4088 |
+
{
|
| 4089 |
+
"update": 2275,
|
| 4090 |
+
"global_step": 9318400,
|
| 4091 |
+
"num_episodes": 3341,
|
| 4092 |
+
"mean_reward": 516.5512644720078,
|
| 4093 |
+
"mean_length": 2668.78,
|
| 4094 |
+
"loss": 10.443692207336426,
|
| 4095 |
+
"sps": 381.5541543957095
|
| 4096 |
+
},
|
| 4097 |
+
{
|
| 4098 |
+
"update": 2280,
|
| 4099 |
+
"global_step": 9338880,
|
| 4100 |
+
"num_episodes": 3349,
|
| 4101 |
+
"mean_reward": 462.85379876613615,
|
| 4102 |
+
"mean_length": 2668.78,
|
| 4103 |
+
"loss": 442.84942626953125,
|
| 4104 |
+
"sps": 279.7896158892528
|
| 4105 |
+
},
|
| 4106 |
+
{
|
| 4107 |
+
"update": 2285,
|
| 4108 |
+
"global_step": 9359360,
|
| 4109 |
+
"num_episodes": 3360,
|
| 4110 |
+
"mean_reward": 507.16173345565795,
|
| 4111 |
+
"mean_length": 2757.46,
|
| 4112 |
+
"loss": 65.15730285644531,
|
| 4113 |
+
"sps": 265.8172803900086
|
| 4114 |
+
},
|
| 4115 |
+
{
|
| 4116 |
+
"update": 2290,
|
| 4117 |
+
"global_step": 9379840,
|
| 4118 |
+
"num_episodes": 3363,
|
| 4119 |
+
"mean_reward": 507.4162758731842,
|
| 4120 |
+
"mean_length": 2818.63,
|
| 4121 |
+
"loss": 70.9657211303711,
|
| 4122 |
+
"sps": 353.8588588797036
|
| 4123 |
+
},
|
| 4124 |
+
{
|
| 4125 |
+
"update": 2295,
|
| 4126 |
+
"global_step": 9400320,
|
| 4127 |
+
"num_episodes": 3368,
|
| 4128 |
+
"mean_reward": 551.9985440444947,
|
| 4129 |
+
"mean_length": 2959.32,
|
| 4130 |
+
"loss": 5.74236536026001,
|
| 4131 |
+
"sps": 340.8187159543217
|
| 4132 |
+
},
|
| 4133 |
+
{
|
| 4134 |
+
"update": 2300,
|
| 4135 |
+
"global_step": 9420800,
|
| 4136 |
+
"num_episodes": 3377,
|
| 4137 |
+
"mean_reward": 564.7782349967956,
|
| 4138 |
+
"mean_length": 3130.89,
|
| 4139 |
+
"loss": 5.68098783493042,
|
| 4140 |
+
"sps": 383.2875448626093
|
| 4141 |
+
},
|
| 4142 |
+
{
|
| 4143 |
+
"update": 2305,
|
| 4144 |
+
"global_step": 9441280,
|
| 4145 |
+
"num_episodes": 3390,
|
| 4146 |
+
"mean_reward": 594.4548657274246,
|
| 4147 |
+
"mean_length": 3136.03,
|
| 4148 |
+
"loss": 178.03961181640625,
|
| 4149 |
+
"sps": 278.82986749605175
|
| 4150 |
+
},
|
| 4151 |
+
{
|
| 4152 |
+
"update": 2310,
|
| 4153 |
+
"global_step": 9461760,
|
| 4154 |
+
"num_episodes": 3391,
|
| 4155 |
+
"mean_reward": 595.1103666639328,
|
| 4156 |
+
"mean_length": 3234.65,
|
| 4157 |
+
"loss": 73.16796112060547,
|
| 4158 |
+
"sps": 386.1064879014476
|
| 4159 |
+
},
|
| 4160 |
+
{
|
| 4161 |
+
"update": 2315,
|
| 4162 |
+
"global_step": 9482240,
|
| 4163 |
+
"num_episodes": 3397,
|
| 4164 |
+
"mean_reward": 560.5055163288116,
|
| 4165 |
+
"mean_length": 3213.23,
|
| 4166 |
+
"loss": 1437.6278076171875,
|
| 4167 |
+
"sps": 198.45749967938127
|
| 4168 |
+
},
|
| 4169 |
+
{
|
| 4170 |
+
"update": 2320,
|
| 4171 |
+
"global_step": 9502720,
|
| 4172 |
+
"num_episodes": 3411,
|
| 4173 |
+
"mean_reward": 401.03073542118074,
|
| 4174 |
+
"mean_length": 2986.15,
|
| 4175 |
+
"loss": 3.3738672733306885,
|
| 4176 |
+
"sps": 1083.0313220969133
|
| 4177 |
+
},
|
| 4178 |
+
{
|
| 4179 |
+
"update": 2325,
|
| 4180 |
+
"global_step": 9523200,
|
| 4181 |
+
"num_episodes": 3412,
|
| 4182 |
+
"mean_reward": 413.53732123851773,
|
| 4183 |
+
"mean_length": 3083.93,
|
| 4184 |
+
"loss": 21.815982818603516,
|
| 4185 |
+
"sps": 659.8576311368523
|
| 4186 |
+
},
|
| 4187 |
+
{
|
| 4188 |
+
"update": 2330,
|
| 4189 |
+
"global_step": 9543680,
|
| 4190 |
+
"num_episodes": 3413,
|
| 4191 |
+
"mean_reward": 407.9750119304657,
|
| 4192 |
+
"mean_length": 3002.15,
|
| 4193 |
+
"loss": 0.47333452105522156,
|
| 4194 |
+
"sps": 726.1803705441753
|
| 4195 |
+
},
|
| 4196 |
+
{
|
| 4197 |
+
"update": 2335,
|
| 4198 |
+
"global_step": 9564160,
|
| 4199 |
+
"num_episodes": 3420,
|
| 4200 |
+
"mean_reward": 454.97729597568514,
|
| 4201 |
+
"mean_length": 3001.83,
|
| 4202 |
+
"loss": 0.5463234186172485,
|
| 4203 |
+
"sps": 582.7651222934119
|
| 4204 |
+
},
|
| 4205 |
+
{
|
| 4206 |
+
"update": 2340,
|
| 4207 |
+
"global_step": 9584640,
|
| 4208 |
+
"num_episodes": 3454,
|
| 4209 |
+
"mean_reward": 401.5923653173447,
|
| 4210 |
+
"mean_length": 2474.53,
|
| 4211 |
+
"loss": 0.9732112884521484,
|
| 4212 |
+
"sps": 190.63133488811127
|
| 4213 |
+
},
|
| 4214 |
+
{
|
| 4215 |
+
"update": 2345,
|
| 4216 |
+
"global_step": 9605120,
|
| 4217 |
+
"num_episodes": 3475,
|
| 4218 |
+
"mean_reward": 180.83635659217833,
|
| 4219 |
+
"mean_length": 1855.64,
|
| 4220 |
+
"loss": 0.047050729393959045,
|
| 4221 |
+
"sps": 497.0424644143239
|
| 4222 |
+
},
|
| 4223 |
+
{
|
| 4224 |
+
"update": 2350,
|
| 4225 |
+
"global_step": 9625600,
|
| 4226 |
+
"num_episodes": 3482,
|
| 4227 |
+
"mean_reward": 181.7909957742691,
|
| 4228 |
+
"mean_length": 1925.71,
|
| 4229 |
+
"loss": 1.1374897956848145,
|
| 4230 |
+
"sps": 853.7958489004412
|
| 4231 |
+
},
|
| 4232 |
+
{
|
| 4233 |
+
"update": 2355,
|
| 4234 |
+
"global_step": 9646080,
|
| 4235 |
+
"num_episodes": 3489,
|
| 4236 |
+
"mean_reward": 158.73119886875153,
|
| 4237 |
+
"mean_length": 1914.03,
|
| 4238 |
+
"loss": 1.258785605430603,
|
| 4239 |
+
"sps": 551.9084865795908
|
| 4240 |
+
},
|
| 4241 |
+
{
|
| 4242 |
+
"update": 2360,
|
| 4243 |
+
"global_step": 9666560,
|
| 4244 |
+
"num_episodes": 3502,
|
| 4245 |
+
"mean_reward": 98.6479220199585,
|
| 4246 |
+
"mean_length": 1635.16,
|
| 4247 |
+
"loss": 0.43499165773391724,
|
| 4248 |
+
"sps": 419.3776501549414
|
| 4249 |
+
},
|
| 4250 |
+
{
|
| 4251 |
+
"update": 2365,
|
| 4252 |
+
"global_step": 9687040,
|
| 4253 |
+
"num_episodes": 3515,
|
| 4254 |
+
"mean_reward": 66.50108590602875,
|
| 4255 |
+
"mean_length": 1518.13,
|
| 4256 |
+
"loss": 166.75491333007812,
|
| 4257 |
+
"sps": 281.0402931910567
|
| 4258 |
+
},
|
| 4259 |
+
{
|
| 4260 |
+
"update": 2370,
|
| 4261 |
+
"global_step": 9707520,
|
| 4262 |
+
"num_episodes": 3528,
|
| 4263 |
+
"mean_reward": 33.59190697193146,
|
| 4264 |
+
"mean_length": 1331.87,
|
| 4265 |
+
"loss": 274.23516845703125,
|
| 4266 |
+
"sps": 287.97774743130026
|
| 4267 |
+
},
|
| 4268 |
+
{
|
| 4269 |
+
"update": 2375,
|
| 4270 |
+
"global_step": 9728000,
|
| 4271 |
+
"num_episodes": 3538,
|
| 4272 |
+
"mean_reward": 23.649227323532106,
|
| 4273 |
+
"mean_length": 1328.19,
|
| 4274 |
+
"loss": 24.9585018157959,
|
| 4275 |
+
"sps": 656.234816203577
|
| 4276 |
+
},
|
| 4277 |
+
{
|
| 4278 |
+
"update": 2380,
|
| 4279 |
+
"global_step": 9748480,
|
| 4280 |
+
"num_episodes": 3539,
|
| 4281 |
+
"mean_reward": 24.15320231437683,
|
| 4282 |
+
"mean_length": 1427.05,
|
| 4283 |
+
"loss": 13.851099967956543,
|
| 4284 |
+
"sps": 840.3197888208443
|
| 4285 |
+
},
|
| 4286 |
+
{
|
| 4287 |
+
"update": 2385,
|
| 4288 |
+
"global_step": 9768960,
|
| 4289 |
+
"num_episodes": 3553,
|
| 4290 |
+
"mean_reward": 25.30362526893616,
|
| 4291 |
+
"mean_length": 1552.4,
|
| 4292 |
+
"loss": -0.07959967106580734,
|
| 4293 |
+
"sps": 348.5790453337399
|
| 4294 |
+
},
|
| 4295 |
+
{
|
| 4296 |
+
"update": 2390,
|
| 4297 |
+
"global_step": 9789440,
|
| 4298 |
+
"num_episodes": 3575,
|
| 4299 |
+
"mean_reward": 43.762970843315124,
|
| 4300 |
+
"mean_length": 1834.94,
|
| 4301 |
+
"loss": 256.5601806640625,
|
| 4302 |
+
"sps": 314.0190386184578
|
| 4303 |
+
},
|
| 4304 |
+
{
|
| 4305 |
+
"update": 2395,
|
| 4306 |
+
"global_step": 9809920,
|
| 4307 |
+
"num_episodes": 3584,
|
| 4308 |
+
"mean_reward": 41.22667598724365,
|
| 4309 |
+
"mean_length": 1832.99,
|
| 4310 |
+
"loss": 37.159915924072266,
|
| 4311 |
+
"sps": 261.015177859497
|
| 4312 |
+
},
|
| 4313 |
+
{
|
| 4314 |
+
"update": 2400,
|
| 4315 |
+
"global_step": 9830400,
|
| 4316 |
+
"num_episodes": 3593,
|
| 4317 |
+
"mean_reward": 56.500927686691284,
|
| 4318 |
+
"mean_length": 1809.72,
|
| 4319 |
+
"loss": 949.2464599609375,
|
| 4320 |
+
"sps": 236.54852291533763
|
| 4321 |
+
},
|
| 4322 |
+
{
|
| 4323 |
+
"update": 2405,
|
| 4324 |
+
"global_step": 9850880,
|
| 4325 |
+
"num_episodes": 3599,
|
| 4326 |
+
"mean_reward": 105.25954935073852,
|
| 4327 |
+
"mean_length": 1813.21,
|
| 4328 |
+
"loss": 1035.45751953125,
|
| 4329 |
+
"sps": 654.1456293848414
|
| 4330 |
+
},
|
| 4331 |
+
{
|
| 4332 |
+
"update": 2410,
|
| 4333 |
+
"global_step": 9871360,
|
| 4334 |
+
"num_episodes": 3608,
|
| 4335 |
+
"mean_reward": 174.8251446390152,
|
| 4336 |
+
"mean_length": 1969.27,
|
| 4337 |
+
"loss": 12.137419700622559,
|
| 4338 |
+
"sps": 374.5700328217855
|
| 4339 |
+
},
|
| 4340 |
+
{
|
| 4341 |
+
"update": 2415,
|
| 4342 |
+
"global_step": 9891840,
|
| 4343 |
+
"num_episodes": 3613,
|
| 4344 |
+
"mean_reward": 174.6033950281143,
|
| 4345 |
+
"mean_length": 2093.28,
|
| 4346 |
+
"loss": 470.9022216796875,
|
| 4347 |
+
"sps": 829.3315456709553
|
| 4348 |
+
},
|
| 4349 |
+
{
|
| 4350 |
+
"update": 2420,
|
| 4351 |
+
"global_step": 9912320,
|
| 4352 |
+
"num_episodes": 3614,
|
| 4353 |
+
"mean_reward": 175.19530655384062,
|
| 4354 |
+
"mean_length": 2188.0,
|
| 4355 |
+
"loss": 7.125182628631592,
|
| 4356 |
+
"sps": 1392.3792980312514
|
| 4357 |
+
},
|
| 4358 |
+
{
|
| 4359 |
+
"update": 2425,
|
| 4360 |
+
"global_step": 9932800,
|
| 4361 |
+
"num_episodes": 3616,
|
| 4362 |
+
"mean_reward": 175.76038108348845,
|
| 4363 |
+
"mean_length": 2285.88,
|
| 4364 |
+
"loss": 11.183570861816406,
|
| 4365 |
+
"sps": 303.2125684013846
|
| 4366 |
+
},
|
| 4367 |
+
{
|
| 4368 |
+
"update": 2430,
|
| 4369 |
+
"global_step": 9953280,
|
| 4370 |
+
"num_episodes": 3625,
|
| 4371 |
+
"mean_reward": 245.62015884399415,
|
| 4372 |
+
"mean_length": 2481.25,
|
| 4373 |
+
"loss": 72.24958038330078,
|
| 4374 |
+
"sps": 223.82439359999108
|
| 4375 |
+
},
|
| 4376 |
+
{
|
| 4377 |
+
"update": 2435,
|
| 4378 |
+
"global_step": 9973760,
|
| 4379 |
+
"num_episodes": 3640,
|
| 4380 |
+
"mean_reward": 12.841221110026042,
|
| 4381 |
+
"mean_length": 242.8,
|
| 4382 |
+
"loss": 39.742530822753906,
|
| 4383 |
+
"sps": 444.8952550886448
|
| 4384 |
+
},
|
| 4385 |
+
{
|
| 4386 |
+
"update": 2440,
|
| 4387 |
+
"global_step": 9994240,
|
| 4388 |
+
"num_episodes": 3640,
|
| 4389 |
+
"mean_reward": 12.841221110026042,
|
| 4390 |
+
"mean_length": 242.8,
|
| 4391 |
+
"loss": 0.29037195444107056,
|
| 4392 |
+
"sps": 1069.6427524147307
|
| 4393 |
+
},
|
| 4394 |
+
{
|
| 4395 |
+
"update": 2445,
|
| 4396 |
+
"global_step": 10014720,
|
| 4397 |
+
"num_episodes": 3640,
|
| 4398 |
+
"mean_reward": 12.841221110026042,
|
| 4399 |
+
"mean_length": 242.8,
|
| 4400 |
+
"loss": 3.3830156326293945,
|
| 4401 |
+
"sps": 1318.7931203919134
|
| 4402 |
+
},
|
| 4403 |
+
{
|
| 4404 |
+
"update": 2450,
|
| 4405 |
+
"global_step": 10035200,
|
| 4406 |
+
"num_episodes": 3644,
|
| 4407 |
+
"mean_reward": 91.08290822882401,
|
| 4408 |
+
"mean_length": 2296.9473684210525,
|
| 4409 |
+
"loss": 20.516225814819336,
|
| 4410 |
+
"sps": 481.54488129169596
|
| 4411 |
+
},
|
| 4412 |
+
{
|
| 4413 |
+
"update": 2455,
|
| 4414 |
+
"global_step": 10055680,
|
| 4415 |
+
"num_episodes": 3658,
|
| 4416 |
+
"mean_reward": 124.92099246111783,
|
| 4417 |
+
"mean_length": 2621.4848484848485,
|
| 4418 |
+
"loss": 150.3678436279297,
|
| 4419 |
+
"sps": 253.02333051932328
|
| 4420 |
+
},
|
| 4421 |
+
{
|
| 4422 |
+
"update": 2460,
|
| 4423 |
+
"global_step": 10076160,
|
| 4424 |
+
"num_episodes": 3665,
|
| 4425 |
+
"mean_reward": 104.92156012058258,
|
| 4426 |
+
"mean_length": 2402.575,
|
| 4427 |
+
"loss": 43.09859085083008,
|
| 4428 |
+
"sps": 444.9419436729771
|
| 4429 |
+
},
|
| 4430 |
+
{
|
| 4431 |
+
"update": 2465,
|
| 4432 |
+
"global_step": 10096640,
|
| 4433 |
+
"num_episodes": 3668,
|
| 4434 |
+
"mean_reward": 99.1124037143796,
|
| 4435 |
+
"mean_length": 2358.6744186046512,
|
| 4436 |
+
"loss": 30.914440155029297,
|
| 4437 |
+
"sps": 564.239378309882
|
| 4438 |
+
},
|
| 4439 |
+
{
|
| 4440 |
+
"update": 2470,
|
| 4441 |
+
"global_step": 10117120,
|
| 4442 |
+
"num_episodes": 3674,
|
| 4443 |
+
"mean_reward": 212.01101287530392,
|
| 4444 |
+
"mean_length": 2689.183673469388,
|
| 4445 |
+
"loss": 519.401611328125,
|
| 4446 |
+
"sps": 400.7113960553138
|
| 4447 |
+
},
|
| 4448 |
+
{
|
| 4449 |
+
"update": 2475,
|
| 4450 |
+
"global_step": 10137600,
|
| 4451 |
+
"num_episodes": 3685,
|
| 4452 |
+
"mean_reward": 246.73736356099445,
|
| 4453 |
+
"mean_length": 2406.016666666667,
|
| 4454 |
+
"loss": 18.674598693847656,
|
| 4455 |
+
"sps": 645.3387661404473
|
| 4456 |
+
},
|
| 4457 |
+
{
|
| 4458 |
+
"update": 2480,
|
| 4459 |
+
"global_step": 10158080,
|
| 4460 |
+
"num_episodes": 3690,
|
| 4461 |
+
"mean_reward": 254.607934988462,
|
| 4462 |
+
"mean_length": 2687.8153846153846,
|
| 4463 |
+
"loss": 227.44029235839844,
|
| 4464 |
+
"sps": 409.4558222523011
|
| 4465 |
}
|
| 4466 |
]
|