Offline Reinforcement Learning
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
78.14Normalized Score
64
May 26, 2026
79.25Normalized Score
64
May 26, 2026
110.7Normalized Return
64
Jun 2, 2026
102.4Normalized Return
63
May 29, 2026
99.3Normalized Score
62
Apr 14, 2026
116.5Normalized Return
61
Jun 2, 2026
101.3Normalized Score
61
May 29, 2026
1,248Normalized Score
61
May 29, 2026
95.6Score
55
Feb 26, 2026
113Normalized Score
55
May 29, 2026
90.34Normalized Score
54
May 22, 2026
59.6Normalized Score
54
May 22, 2026
104.5Normalized Score
54
Jun 11, 2026
115.4Normalized Score
54
Jun 2, 2026
104.8Normalized Return
54
Jun 15, 2026
68.4Normalized Score
54
May 29, 2026
61.447Score
53
Mar 4, 2026
117.4Normalized Return
53
May 28, 2026
128.3Normalized Return
53
May 28, 2026
77.9Average Normalized Return
53
Jun 2, 2026
68.2Normalized Score
53
May 29, 2026
97Normalized Score
52
May 11, 2026
105.6Normalized Return
49
May 29, 2026
69.7Normalized Average Return
48
May 29, 2026
114.2Normalized Score
47
Jun 11, 2026