Offline Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
92.8Normalized Score
9
Mar 5, 2026
2,480Normalized Score
9
Mar 5, 2026
78.4Normalized Score
9
Mar 5, 2026
83.692Performance Score
9
Mar 4, 2026
53.87Performance Score
9
Mar 4, 2026
109.803Performance Score
9
Mar 4, 2026
82.786Performance Score
9
Mar 4, 2026
94.578Performance Score
9
Mar 4, 2026
80.904Performance Score
9
Mar 4, 2026
83.692Average Return
9
Mar 4, 2026
53.87Average Return
9
Mar 4, 2026
118.564Average Return
9
Mar 4, 2026
82.363Average Return
9
Mar 4, 2026
80.904Average Return
9
Mar 4, 2026
92.5Cube Single Task 1 Success Rate
9
Mar 4, 2026
104.7Cheetah Run Score
9
Mar 4, 2026
82.9Mean Normalized Score
9
Feb 26, 2026
0.99Average Success Rate
9
Feb 26, 2026
50.3Avg Normalized Return
9
Feb 26, 2026
74.5Average Normalized Return
9
Feb 26, 2026
67.8Avg Normalized Return
9
Feb 26, 2026
112.7Average Reward
9
Feb 26, 2026
45.5HalfCheetah
9
Feb 26, 2026
49.1HalfCheetah Score
9
Feb 26, 2026
92.1HalfCheetah Score
9
Feb 26, 2026