Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Meta-Reinforcement Learning on MuJoCo HalfCheetah Velocity variation (test)

-184CVaR 0.05 Return

RoML

-2,702.88-2,048.94-1,395-741.06Jan 26, 2023
Updated 1mo ago

Evaluation Results

MethodLinks
2023.01
-184
2023.01
-202
2023.01
-725
2023.01
-897
2023.01
-1,089
2023.01
-1,156
2023.01
-2,606