Offline Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
20.43Normalized Score
6
Feb 26, 2026
98.42Normalized Score
6
Feb 26, 2026
58.19Normalized Score
6
Feb 26, 2026
38.87Normalized Score
6
Feb 26, 2026
16.36Normalized Score
6
Feb 26, 2026
98.54Normalized Score
6
Feb 26, 2026
75.61Normalized Score
6
Feb 26, 2026
51.28Normalized Score
6
Feb 26, 2026
97.84Normalized Score
6
Feb 26, 2026
93.16Normalized Score
6
Feb 26, 2026
38.59Normalized Score
6
Feb 26, 2026
30.24Normalized Score
6
Feb 26, 2026
70.45Normalized Score
6
Feb 26, 2026
85.76Normalized Score
6
Feb 26, 2026
92.81Normalized Score
6
Feb 26, 2026
18.23Normalized Score
6
Feb 26, 2026
1,269Return
6
Feb 26, 2026
79.2Walker2d (medium)
6
Feb 26, 2026
47.7HalfCheetah Return
6
Feb 26, 2026
46.3HalfCheetah Return
6
Feb 26, 2026
86.8HalfCheetah Return
6
Feb 26, 2026
869Cartpole Swingup Score
6
Feb 26, 2026
0.85Return
5
Jul 3, 2026
0.96Return
5
Jul 3, 2026
99Return
5
Jul 3, 2026