Offline Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
97.29Normalized Return
7
Feb 26, 2026
93.5Normalized Return
7
Feb 26, 2026
111.71Normalized Return
7
Feb 26, 2026
106.17Normalized Return
7
Feb 26, 2026
0.829Normalized Return
7
Feb 26, 2026
129Normalized Score
7
Feb 26, 2026
121.2Normalized Score
7
Feb 26, 2026
69.6Normalized Score
7
Feb 26, 2026
102.7Normalized Score
7
Feb 26, 2026
31.3Normalized Score
7
Feb 26, 2026
108.8Normalized Score
7
Feb 26, 2026
95.3Normalized Score
7
Feb 26, 2026
18.8Normalized Score
7
Feb 26, 2026
62.3Normalized Score
7
Feb 26, 2026
4.6Normalized Score
7
Feb 26, 2026
113.2Normalized Score
7
Feb 26, 2026
63.4Normalized Score
7
Feb 26, 2026
58.6Normalized Score
7
Feb 26, 2026
59.4Normalized Score
7
Feb 26, 2026
4.8Normalized Score
7
Feb 26, 2026
91.7Normalized Score
7
Feb 26, 2026
63Normalized Score
7
Feb 26, 2026
31.1Normalized Score
7
Feb 26, 2026
46Normalized Score
7
Feb 26, 2026
0.067Normalized Score
7
Feb 26, 2026