Skip to main content

Slimshadys's group workspace

Timestamps visible
2023-12-11 14:29:03
--------BEGIN ITERATION REPORT--------
2023-12-11 14:29:03
Policy Reward: 60,89827
2023-12-11 14:29:03
Policy Entropy: 0,16845
2023-12-11 14:29:03
Value Function Loss: 0,38490
2023-12-11 14:29:03
Mean KL Divergence: 0,00892
2023-12-11 14:29:03
SB3 Clip Fraction: 0,04905
2023-12-11 14:29:03
Policy Update Magnitude: 0,17879
2023-12-11 14:29:03
Value Function Update Magnitude: 0,26045
2023-12-11 14:29:03
Collected Steps per Second: 8.575,74254
2023-12-11 14:29:03
Overall Steps per Second: 6.561,45925
2023-12-11 14:29:03
Timestep Collection Time: 5,83460
2023-12-11 14:29:03
Timestep Consumption Time: 1,79115
2023-12-11 14:29:03
PPO Batch Consumption Time: 0,14932
2023-12-11 14:29:03
Total Iteration Time: 7,62574
2023-12-11 14:29:03
Cumulative Model Updates: 3.459
2023-12-11 14:29:03
Cumulative Timesteps: 57.726.930
2023-12-11 14:29:03
Timesteps Collected: 50.036
2023-12-11 14:29:03
--------END ITERATION REPORT--------
2023-12-11 14:29:03
Saving checkpoint 57726930...
2023-12-11 14:29:03
Checkpoint 57726930 saved!