Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Offline Control on Heterogeneous Pendulum Rich-Data 600,000 transition steps

-0.6Cumulative Reward

AOC

-671.5248-497.3424-323.16-148.9776Oct 11, 2023
Updated 4d ago

Evaluation Results

MethodLinks
2023.10
-0.6
2023.10
-1.41
2023.10
-15.27
2023.10
-126.74
2023.10
-208.81
2023.10
-512.71
2023.10
-645.72