Offline Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
102Normalized Score
14
Mar 18, 2026
69.8HalfCheetah-Medium Return
13
May 12, 2026
76.3Score
13
Mar 19, 2026
100.2Performance Score
13
Mar 19, 2026
90.5Score
13
Mar 19, 2026
133.8Score
13
Feb 26, 2026
9.9Normalized Score
13
Feb 26, 2026
68.2Normalized Score
13
Feb 26, 2026
69.5Normalized Score
13
Feb 26, 2026
95.4Normalized Score
13
Feb 26, 2026
40.7Normalized Score
13
Feb 26, 2026
82Normalized Score
13
Feb 26, 2026
133.8Normalized Score
13
Feb 26, 2026
102.6Normalized Score
13
Feb 26, 2026
98.3Normalized Score
13
Feb 26, 2026
83.1Normalized Score
13
Feb 26, 2026
82.4Normalized Score
13
Feb 26, 2026
139.5Normalized Score
13
Feb 26, 2026
71.12Average Return (All Settings)
13
May 15, 2026
98Test Return
12
May 15, 2026
47Test Return
12
May 15, 2026
79Test Return
12
May 15, 2026
0.6Normalized Score
12
Feb 26, 2026
211.31Episodic Return
12
Feb 26, 2026
1,002.09Episodic Return
12
Feb 26, 2026