Skip to main content

Slimshadys's group workspace

Timestamps visible
2023-12-13 10:02:59
--------BEGIN ITERATION REPORT--------
2023-12-13 10:02:59
Policy Reward: 129,31702
2023-12-13 10:02:59
Policy Entropy: 0,11072
2023-12-13 10:02:59
Value Function Loss: 2,80725
2023-12-13 10:02:59
Mean KL Divergence: 0,00810
2023-12-13 10:02:59
SB3 Clip Fraction: 0,03710
2023-12-13 10:02:59
Policy Update Magnitude: 0,07622
2023-12-13 10:02:59
Value Function Update Magnitude: 0,06169
2023-12-13 10:02:59
Collected Steps per Second: 8.475,03388
2023-12-13 10:02:59
Overall Steps per Second: 6.364,53434
2023-12-13 10:02:59
Timestep Collection Time: 5,90204
2023-12-13 10:02:59
Timestep Consumption Time: 1,95714
2023-12-13 10:02:59
PPO Batch Consumption Time: 0,15284
2023-12-13 10:02:59
Total Iteration Time: 7,85918
2023-12-13 10:02:59
Cumulative Model Updates: 2.945
2023-12-13 10:02:59
Cumulative Timesteps: 49.172.934
2023-12-13 10:02:59
Timesteps Collected: 50.020
2023-12-13 10:02:59
--------END ITERATION REPORT--------
2023-12-13 10:02:59
Saving checkpoint 49172934...
2023-12-13 10:02:59
Checkpoint 49172934 saved!