Skip to main content

Slimshadys's group workspace

Timestamps visible
2023-12-04 21:48:09
--------BEGIN ITERATION REPORT--------
2023-12-04 21:48:09
Policy Reward: 94,02401
2023-12-04 21:48:09
Policy Entropy: 3,73593
2023-12-04 21:48:09
Value Function Loss: 0,08204
2023-12-04 21:48:09
Mean KL Divergence: 0,00760
2023-12-04 21:48:09
SB3 Clip Fraction: 0,08489
2023-12-04 21:48:09
Policy Update Magnitude: 0,24269
2023-12-04 21:48:09
Value Function Update Magnitude: 0,33260
2023-12-04 21:48:09
Collected Steps per Second: 5.065,99587
2023-12-04 21:48:09
Overall Steps per Second: 4.168,34207
2023-12-04 21:48:09
Timestep Collection Time: 9,87131
2023-12-04 21:48:09
Timestep Consumption Time: 2,12579
2023-12-04 21:48:09
PPO Batch Consumption Time: 0,34369
2023-12-04 21:48:09
Total Iteration Time: 11,99710
2023-12-04 21:48:09
Cumulative Model Updates: 892
2023-12-04 21:48:09
Cumulative Timesteps: 22.359.056
2023-12-04 21:48:09
Timesteps Collected: 50.008
2023-12-04 21:48:09
--------END ITERATION REPORT--------
2023-12-04 21:48:09
Saving checkpoint 22359056...
2023-12-04 21:48:09
Checkpoint 22359056 saved!