Offline Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
40.45Normalized Score
6
Mar 18, 2026
23.92Normalized Score
6
Mar 18, 2026
28.51Normalized Score
6
Mar 18, 2026
27.18Normalized Score
6
Mar 18, 2026
18.8Episode Return
6
Mar 5, 2026
1,286Raw Score
6
Mar 5, 2026
14,013.2Raw Score
6
Mar 5, 2026
111Episode Return
6
Mar 5, 2026
29.75Mean Score
6
Mar 4, 2026
0.23Error Rate
6
Mar 4, 2026
81.5IQM
6
Mar 4, 2026
28.06Score (L0.1)
6
Feb 26, 2026
37.68Normalized Score (Level 0.1)
6
Feb 26, 2026
30.4Normalized Score (Level 0.1)
6
Feb 26, 2026
71.41Score (Level 0.1)
6
Feb 26, 2026
58.95Normalized Score (Level 0.1)
6
Feb 26, 2026
25.58Score (Level 0.1)
6
Feb 26, 2026
26.39Score (L0.1)
6
Feb 26, 2026
14.09Normalized Score (Level 0.1)
6
Feb 26, 2026
81.9Mean Normalized Return
6
Feb 26, 2026
54.1Mean Normalized Return
6
Feb 26, 2026
63.1Mean Normalized Return
6
Feb 26, 2026
65Mean Normalized Return
6
Feb 26, 2026
72.1Mean Normalized Return
6
Feb 26, 2026
28.5Mean Normalized Return
6
Feb 26, 2026