Skip to main content

Slimshadys's group workspace

Timestamps visible
2023-12-08 22:36:09
--------BEGIN ITERATION REPORT--------
2023-12-08 22:36:09
Policy Reward: 15,40718
2023-12-08 22:36:09
Policy Entropy: 0,23502
2023-12-08 22:36:09
Value Function Loss: 0,43022
2023-12-08 22:36:09
Mean KL Divergence: 0,00263
2023-12-08 22:36:09
SB3 Clip Fraction: 0,02825
2023-12-08 22:36:09
Policy Update Magnitude: 0,11576
2023-12-08 22:36:09
Value Function Update Magnitude: 0,15486
2023-12-08 22:36:09
Collected Steps per Second: 6.951,34862
2023-12-08 22:36:09
Overall Steps per Second: 5.524,17814
2023-12-08 22:36:09
Timestep Collection Time: 7,19774
2023-12-08 22:36:09
Timestep Consumption Time: 1,85953
2023-12-08 22:36:09
PPO Batch Consumption Time: 0,15828
2023-12-08 22:36:09
Total Iteration Time: 9,05727
2023-12-08 22:36:09
Cumulative Model Updates: 1.295
2023-12-08 22:36:09
Cumulative Timesteps: 32.413.668
2023-12-08 22:36:09
Timesteps Collected: 50.034
2023-12-08 22:36:09
--------END ITERATION REPORT--------
2023-12-08 22:36:09
Saving checkpoint 32413668...
2023-12-08 22:36:09
Checkpoint 32413668 saved!