Offline Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
42.6Normalized Score
4
Feb 26, 2026
2,578.5Average Return
4
Feb 26, 2026
66.5Hopper-Medium Score
4
Feb 26, 2026
42.4Score
4
Feb 26, 2026
42.9Score
4
Feb 26, 2026
135.9Normalized Score
4
Feb 26, 2026
92.7Normalized Score
4
Feb 26, 2026
136.2Normalized Score
4
Feb 26, 2026
104.8Normalized Score
4
Feb 26, 2026
31.62Ant Return (Random)
4
Feb 26, 2026
53.3Averaged Score
4
Feb 26, 2026
62Averaged Score
4
Feb 26, 2026
76.7Averaged Score
4
Feb 26, 2026
89.3Averaged Score
4
Feb 26, 2026
71.4Normalized Score
4
Feb 26, 2026
85.5Normalized Score
4
Feb 26, 2026
73.2Avg Normalized Score
4
May 29, 2026
45Normalized Score
3
May 29, 2026
375Return
3
Feb 26, 2026
366Return
3
Feb 26, 2026
48.3Minari Adroit Score
3
Feb 26, 2026
67.4Normalized Score
3
Feb 26, 2026
45.3Normalized Score
3
Feb 26, 2026
13.6Normalized Score
3
Feb 26, 2026
40.1Normalized Score
3
Feb 26, 2026