Skip to main content

Slimshadys's group workspace

Timestamps visible
2023-12-05 18:26:14
--------BEGIN ITERATION REPORT--------
2023-12-05 18:26:14
Policy Reward: 8,13186
2023-12-05 18:26:14
Policy Entropy: 1,19667
2023-12-05 18:26:14
Value Function Loss: 0,89667
2023-12-05 18:26:14
Mean KL Divergence: 0,02681
2023-12-05 18:26:14
SB3 Clip Fraction: 0,08485
2023-12-05 18:26:14
Policy Update Magnitude: 0,21405
2023-12-05 18:26:14
Value Function Update Magnitude: 0,22279
2023-12-05 18:26:14
Collected Steps per Second: 7.595,48921
2023-12-05 18:26:14
Overall Steps per Second: 5.999,40459
2023-12-05 18:26:14
Timestep Collection Time: 6,58733
2023-12-05 18:26:14
Timestep Consumption Time: 1,75250
2023-12-05 18:26:14
PPO Batch Consumption Time: 0,15530
2023-12-05 18:26:14
Total Iteration Time: 8,33983
2023-12-05 18:26:14
Cumulative Model Updates: 1.579
2023-12-05 18:26:14
Cumulative Timesteps: 39.516.720
2023-12-05 18:26:14
Timesteps Collected: 50.034
2023-12-05 18:26:14
--------END ITERATION REPORT--------
2023-12-05 18:26:14
Saving checkpoint 39516720...
2023-12-05 18:26:14
Checkpoint 39516720 saved!