Offline Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
87AntMaze Large Navigate Score (Single Task)
11
May 27, 2026
94D4RL Score
11
May 26, 2026
0.93D4RL Score
11
May 26, 2026
94Normalized Return
11
May 14, 2026
45Normalized Return
11
May 14, 2026
49Normalized Return
11
May 14, 2026
1.11Normalized Return
11
May 14, 2026
92Normalized Return
11
May 14, 2026
85Normalized Return
11
May 14, 2026
1.1Normalized Return
11
May 14, 2026
0.87Normalized Return
11
May 14, 2026
69Normalized Return
11
May 14, 2026
117.7Normalized Average Return
11
May 14, 2026
113.2Normalized Average Return
11
May 14, 2026
110Normalized Return
11
May 14, 2026
98.4Normalized Return
11
May 14, 2026
109.6Normalized Average Return
11
May 14, 2026
77.2Normalized Average Return
11
May 14, 2026
93.1Normalized Return
11
May 14, 2026
107.7Normalized Average Return
11
May 14, 2026
80Normalized Return
11
May 14, 2026
37.3Normalized Average Return
11
May 14, 2026
12.8Normalized Score
11
May 12, 2026
31.2Normalized Score
11
May 12, 2026
58Normalized Score
11
Apr 27, 2026