Offline Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
23.1Normalized Score
7
Feb 26, 2026
20.3Normalized Score
7
Feb 26, 2026
6.7HalfCheetah (r) Score
7
Feb 26, 2026
126.8Normalized Score
7
Feb 26, 2026
120Normalized Score
7
Feb 26, 2026
119Normalized Score
7
Feb 26, 2026
58.2Normalized Score
7
Feb 26, 2026
98.9Normalized Score
7
Feb 26, 2026
98Score
7
Feb 26, 2026
73.2Hopper (Medium) Return
7
Feb 26, 2026
100.5Hopper High Score
7
Feb 26, 2026
77.21Average Score
7
Mar 18, 2026
103.87Average Score
7
Mar 18, 2026
107Avg Normalized Score
7
Feb 26, 2026
102Averaged Normalized Score
7
Feb 26, 2026
99.5umaze Success Rate
7
May 26, 2026
90Normalized Score
7
Feb 26, 2026
0.23Normalized Score
7
Feb 26, 2026
1.1Normalized Score
7
Feb 26, 2026
113.97Normalized Score
7
Feb 26, 2026
108.43Normalized Score
7
Feb 26, 2026
698Spike
7
Feb 26, 2026
57.6Avg Normalized Score
7
Feb 26, 2026
76.4Avg Normalized Score
7
Feb 26, 2026
91Avg Normalized Score
7
Feb 26, 2026