Offline Reinforcement Learning
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
112.3Normalized Score
47
Jun 11, 2026
0.62Normalized Score
47
Jun 11, 2026
106.6Normalized Score
47
Jun 11, 2026
88Normalized Score
47
May 15, 2026
90Normalized Score
47
Jun 11, 2026
100.6Normalized Score
46
Jun 2, 2026
57.835Return
44
Mar 4, 2026
85.6Score
44
May 29, 2026
85Mixed Success Rate
43
Jun 1, 2026
100.1Normalized Return
43
Feb 26, 2026
121.2Normalized Average Return
43
May 29, 2026
112.8Normalized Avg Return
43
Jun 15, 2026
104.5Normalized Score
42
Jun 15, 2026
398.8Target Domain Score (Normalized)
42
Feb 26, 2026
121.4Normalized Score
42
May 29, 2026
112.7Normalized Avg Return
41
May 29, 2026
-1,026Maximum episode return
40
May 29, 2026
114Normalized Return
40
May 29, 2026
200.6Normalized Performance
39
Jun 15, 2026
179.2Normalized Return
38
Feb 26, 2026
141Normalized Return
38
Feb 26, 2026
117.4Mean Normalized Score
38
May 11, 2026
109.4Normalized Score
36
Jun 2, 2026
104.4Avg Normalized Score
36
Mar 10, 2026
112.8Normalized Return
36
May 12, 2026