Skip to main content

Slimshadys's group workspace

Timestamps visible
2023-12-10 11:14:08
--------BEGIN ITERATION REPORT--------
2023-12-10 11:14:08
Policy Reward: 104,91997
2023-12-10 11:14:08
Policy Entropy: 2,36759
2023-12-10 11:14:08
Value Function Loss: 0,36248
2023-12-10 11:14:08
Mean KL Divergence: 0,01278
2023-12-10 11:14:08
SB3 Clip Fraction: 0,14529
2023-12-10 11:14:08
Policy Update Magnitude: 0,35526
2023-12-10 11:14:08
Value Function Update Magnitude: 0,29152
2023-12-10 11:14:08
Collected Steps per Second: 8.603,29040
2023-12-10 11:14:08
Overall Steps per Second: 6.408,34802
2023-12-10 11:14:08
Timestep Collection Time: 5,81243
2023-12-10 11:14:08
Timestep Consumption Time: 1,99083
2023-12-10 11:14:08
PPO Batch Consumption Time: 0,15170
2023-12-10 11:14:08
Total Iteration Time: 7,80326
2023-12-10 11:14:08
Cumulative Model Updates: 1.659
2023-12-10 11:14:08
Cumulative Timesteps: 27.712.958
2023-12-10 11:14:08
Timesteps Collected: 50.006
2023-12-10 11:14:08
--------END ITERATION REPORT--------
2023-12-10 11:14:08
Saving checkpoint 27712958...
2023-12-10 11:14:08
Checkpoint 27712958 saved!