Offline Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
114Normalized Score
35
May 29, 2026
45.4Normalized Score
35
Jun 2, 2026
23.5Normalized Score
35
Jun 2, 2026
38.1Normalized Score
35
Jun 2, 2026
1,392.93Reward
35
Feb 26, 2026
66.8Score (HalfCheetah, Medium)
34
Feb 26, 2026
91.7Normalized Score
33
Jun 11, 2026
69.1Normalized Score
33
Jun 11, 2026
52.2Score
33
Apr 27, 2026
97Average Success Rate
33
May 12, 2026
96.8Normalized Return
33
Feb 26, 2026
107.4Normalized Score
33
Jun 2, 2026
111Normalized Score
33
Jun 2, 2026
52.94Normalized Score
32
May 26, 2026
76.96Normalized Score
32
May 26, 2026
69.48Normalized Score
32
May 26, 2026
62.41Normalized Score
32
May 26, 2026
72.13Normalized Score
32
May 26, 2026
100.8Average Score
32
Feb 26, 2026
86.7Return
32
Feb 26, 2026
56Average Score
32
Feb 26, 2026
116.6Mean Normalized Score
32
May 11, 2026
100.7Reward
32
May 8, 2026
117.2Average Normalized Score
31
Mar 10, 2026
107.4Avg Normalized Score
31
Mar 10, 2026