Offline Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
62.6Mean Normalized Return
6
Feb 26, 2026
77.24Aggregate Score
6
Feb 26, 2026
84.3HalfCheetah Return
6
Feb 26, 2026
105.9HalfCheetah
6
Feb 26, 2026
30.9HalfCheetah
6
Feb 26, 2026
0.01Runtime (s)
6
Feb 26, 2026
0.01Runtime (s)
6
Feb 26, 2026
0.005Runtime (s)
6
Feb 26, 2026
107.3Normalized Score
6
Feb 26, 2026
1.541Normalized Score
6
Feb 26, 2026
66.8Normalized Score
6
Feb 26, 2026
43.8Normalized Score
6
Feb 26, 2026
74.3Normalized Score
6
Feb 26, 2026
47.1Normalized Score
6
Feb 26, 2026
106Normalized Score
6
Feb 26, 2026
94.9Normalized Score
6
Feb 26, 2026
7.86Average True Return
6
Feb 26, 2026
-1.94Average True Return
6
Feb 26, 2026
7,989Return
6
Feb 26, 2026
4,114Return
6
Feb 26, 2026
1,515Return
6
Feb 26, 2026
412Return
6
Feb 26, 2026
3,907Return
6
Feb 26, 2026
1,676Return
6
Feb 26, 2026
685Return
6
Feb 26, 2026