Offline Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
84Normalized Average Return
14
May 29, 2026
100Normalized Score
14
May 29, 2026
95Normalized Return
14
Feb 26, 2026
70.67Normalized Return
14
Feb 26, 2026
51.2Normalized Score
14
Mar 4, 2026
120.3Normalized Score
14
Feb 26, 2026
69.6Normalized Score
14
Feb 26, 2026
96.4Normalized Score
14
Feb 26, 2026
21.5Normalized Score
14
Feb 26, 2026
33.8Normalized Score
14
Feb 26, 2026
32.2Normalized Score
14
Feb 26, 2026
6.6Average Score
14
May 26, 2026
89.5Average Score
14
May 26, 2026
66.3Average Normalized Score
14
Feb 26, 2026
110.2Normalized Score
14
Feb 26, 2026
86.8Average Normalized Score
14
Feb 26, 2026
95.6Normalized Score
14
Feb 26, 2026
48.3Average Normalized Score
14
Feb 26, 2026
110Average Normalized Score
14
Feb 26, 2026
8,830Avg Normalized Score
14
Feb 26, 2026
88.5Avg Normalized Score
14
Feb 26, 2026
98.6Averaged Normalized Score
14
Feb 26, 2026
5,460Avg Normalized Score
14
May 14, 2026
56.6Avg Normalized Score
14
May 14, 2026
66.8HalfCheetah Score
14
Feb 26, 2026