Offline Reinforcement Learning
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
110Normalized Score
169
May 28, 2026
119.2Normalized Score
161
May 11, 2026
116.1Normalized Score
140
Jun 4, 2026
110.6Normalized Score
109
May 28, 2026
84.3Normalized Score
105
May 11, 2026
106.4Normalized Score
104
May 11, 2026
510Normalized Score
101
May 11, 2026
62.86Normalized Return
97
May 26, 2026
95.8Normalized Score
97
May 11, 2026
45.4Normalized Score
94
May 11, 2026
53.6Normalized Score
86
May 11, 2026
95.5Normalized Return
85
Jun 2, 2026
54AntMaze Giant Navigate
78
Jul 8, 2026
94.4AntMaze Medium Play Return
78
Jun 11, 2026
93.5Normalized Score
74
May 29, 2026
109.7Normalized Return
73
May 29, 2026
109.4Normalized Score
72
May 11, 2026
90.2Normalized Score
69
May 8, 2026
76.9Normalized Score
68
Jun 2, 2026
3,729Normalized Score
68
May 29, 2026
113.7Normalized Score
66
Jun 2, 2026
116.3Normalized Score
66
Jun 2, 2026
118.9Normalized Score
66
Jun 2, 2026
74.8Normalized Return
65
May 29, 2026
66.82Normalized Score
64
May 26, 2026