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

Offline Control on Heterogeneous Pendulum Low-Data 100,000 transition steps

-1.39Cumulative Reward

AOC

-883.3724-654.3962-425.42-196.4438Oct 11, 2023
Updated 4d ago

Evaluation Results

MethodLinks
2023.10
-1.39
2023.10
-1.5
2023.10
-4.1
2023.10
-307.81
2023.10
-422.77
2023.10
-557.07
2023.10
-849.45