Offline Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
62.2Normalized Reward
12
Feb 26, 2026
153.9Normalized Score
12
Feb 26, 2026
85Normalized Score
12
Feb 26, 2026
72.8Normalized Score
12
Feb 26, 2026
209.2Normalized Score
12
Feb 26, 2026
84Normalized Score
12
Feb 26, 2026
609.5Normalized Score
12
Feb 26, 2026
56.6Normalized Score
12
Feb 26, 2026
80.2Normalized Score
12
Feb 26, 2026
84Score (Normalized)
12
Feb 26, 2026
156.4Normalized Score
12
Feb 26, 2026
11,490Normalized Score
12
Feb 26, 2026
13,330Normalized Score
12
Feb 26, 2026
35.6Normalized Score
12
Feb 26, 2026
97.97Normalized Score
12
Feb 26, 2026
96.28Normalized Score
12
Feb 26, 2026
40Normalized Average Return
12
Feb 26, 2026
6.7Normalized Score
12
Feb 26, 2026
76.3Normalized Return
12
Feb 26, 2026
54Success Rate
11
Jun 2, 2026
92Success Rate
11
Jun 2, 2026
36.7Normalized Score
11
May 29, 2026
46.2Normalized Score
11
May 29, 2026
38.5Normalized Score
11
May 29, 2026
119.3Normalized Score
11
May 29, 2026