Skip to main content

Slimshadys's group workspace

Timestamps visible
2024-01-02 13:12:58
--------BEGIN ITERATION REPORT--------
2024-01-02 13:12:58
Policy Reward: 20,31622
2024-01-02 13:12:58
Policy Entropy: 0,05970
2024-01-02 13:12:58
Value Function Loss: 2,23547
2024-01-02 13:12:58
Mean KL Divergence: 0,03108
2024-01-02 13:12:58
SB3 Clip Fraction: 0,04236
2024-01-02 13:12:58
Policy Update Magnitude: 0,05581
2024-01-02 13:12:58
Value Function Update Magnitude: 0,06275
2024-01-02 13:12:58
Collected Steps per Second: 11.217,67152
2024-01-02 13:12:58
Overall Steps per Second: 8.426,39059
2024-01-02 13:12:58
Timestep Collection Time: 4,45904
2024-01-02 13:12:58
Timestep Consumption Time: 1,47708
2024-01-02 13:12:58
PPO Batch Consumption Time: 0,12764
2024-01-02 13:12:58
Total Iteration Time: 5,93611
2024-01-02 13:12:58
Cumulative Model Updates: 4.163
2024-01-02 13:12:58
Cumulative Timesteps: 69.537.198
2024-01-02 13:12:58
Timesteps Collected: 50.020
2024-01-02 13:12:58
--------END ITERATION REPORT--------
2024-01-02 13:12:58
Saving checkpoint 69537198...
2024-01-02 13:12:58
Checkpoint 69537198 saved!