Offline Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
52.2Normalized Return
18
Feb 26, 2026
111.6Normalized Score
18
Feb 26, 2026
95.1Normalized Score
18
Feb 26, 2026
67.5Normalized Score
18
Feb 26, 2026
75.8Normalized Score
18
Feb 26, 2026
116.6Normalized Return
18
Feb 26, 2026
101.1Normalized Return
18
Feb 26, 2026
78.2Score
18
Feb 26, 2026
92.7Normalized Score
18
Mar 18, 2026
30Success Rate
17
May 8, 2026
87.6Average Score
17
Feb 26, 2026
95.5Normalized Score
17
Mar 10, 2026
23.6Normalized Score
17
Mar 10, 2026
94.3Normalized Score
17
Feb 26, 2026
10,364.36Avg True Return
17
Jun 2, 2026
48.11Reward
17
Feb 26, 2026
108.4Normalized Return
17
Feb 26, 2026
88.5Normalized Return
17
Feb 26, 2026
0.9Normalized Score
17
Feb 26, 2026
75.1Normalized Avg Return
17
Feb 26, 2026
94.9Normalized Score
16
May 11, 2026
67.24Final Return
16
Feb 26, 2026
120Score
16
Feb 26, 2026
106Score
16
Feb 26, 2026
97Score
16
Feb 26, 2026