Offline Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
58Average Episodic Return
7
Apr 9, 2026
49Average Episodic Return
7
Apr 9, 2026
66Average Episodic Return
7
Apr 9, 2026
86Average Episodic Return
7
Apr 9, 2026
71Average Episodic Return
7
Apr 9, 2026
85.4Final Score
7
Mar 19, 2026
87.5Normalized Score
7
Mar 10, 2026
70.7Normalized Score
7
Mar 10, 2026
7.64Return
7
Mar 5, 2026
23Success Rate
7
Mar 4, 2026
13Success Rate
7
Mar 4, 2026
13Success Rate
7
Mar 4, 2026
87Success Rate
7
Mar 4, 2026
76.45Normalized Return
7
Feb 26, 2026
90.67Normalized Return
7
Feb 26, 2026
74.04Normalized Return
7
Feb 26, 2026
70.6Normalized Return
7
Feb 26, 2026
81.33Normalized Return
7
Feb 26, 2026
71.33Normalized Return
7
Feb 26, 2026
79.57Normalized Return
7
Feb 26, 2026
65.85Normalized Return
7
Feb 26, 2026
61.49Normalized Return
7
Feb 26, 2026
72.47Normalized Return
7
Feb 26, 2026
98.5Normalized Return
7
Feb 26, 2026
109.6Normalized Return
7
Feb 26, 2026