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

Offline Reinforcement Learning on D4RL Walker-medium-expert v2

113Normalized Return

Onestep

72.9683.35593.75104.145Feb 13, 2022Oct 10, 2022Jun 7, 2023Feb 2, 2024Sep 29, 2024May 27, 2025Jan 22, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2022.02
113
2022.02
112
2026.01
110.4
2022.02
110.1
2026.01
110.1
2026.01
109.8
2022.02
109.6
2026.01
109.6
2026.01
109.5
2022.02
108.8
2026.01
108.6
2022.02
108.1
2022.02
107.5
2026.01
98.7
2026.01
81.6
2022.02
74.5