Offline Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
79.6Score
16
Feb 26, 2026
82.3Normalized Reward
16
Feb 26, 2026
48.9Normalized Score
16
Feb 26, 2026
84.7Normalized Score
16
Feb 26, 2026
73.1HalfCheetah Medium Score
16
Mar 5, 2026
776.7Mean Episode Reward
16
Feb 26, 2026
2,116.2Average Return
16
Feb 26, 2026
2,278.9Average Return
16
Feb 26, 2026
7,357.5Average Return
16
Feb 26, 2026
113Normalized Return
16
Feb 26, 2026
35.6Return (Hopper, Random)
16
Mar 25, 2026
109.1Normalized Return
16
Feb 26, 2026
100Returns
15
Apr 9, 2026
97Cumulative Returns
15
Apr 9, 2026
81.8Normalized Score
15
May 14, 2026
1,020.7Total Score
15
Feb 26, 2026
88.1Normalized Score
15
Jun 11, 2026
105.9Avg Normalized Return
15
Feb 26, 2026
90.7Average Return
15
Feb 26, 2026
453.64Mean Return
14
Jun 15, 2026
778Mean Return
14
Jun 15, 2026
2,696.61Mean Return
14
Jun 15, 2026
1,513.27Mean Reward
14
Jun 15, 2026
3,567.89Mean Return
14
Jun 15, 2026
5,659.4Mean Return
14
Jun 15, 2026