Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
-806.73Reward
7
Feb 26, 2026
9.57Mean Performance
7
Feb 26, 2026
9.74Mean Score
7
Feb 26, 2026
443.53Acrobot Swingup
7
Feb 26, 2026
544.86Dog Run
7
Feb 26, 2026
-19Average Final Return
7
Feb 26, 2026
9,360Average Final Return
7
Feb 26, 2026
-10.2Reward
7
Feb 26, 2026
2,674Reward
7
Feb 26, 2026
5,193Reward
7
Feb 26, 2026
11,515Reward
7
Feb 26, 2026
-9.5Reward
7
Feb 26, 2026
4,409Reward
7
Feb 26, 2026
3,472Reward
7
Feb 26, 2026
4,093Reward
7
Feb 26, 2026
-7.1Average Return
7
Feb 26, 2026
1,267Average Return
7
Feb 26, 2026
990Average Return
7
Feb 26, 2026
4,896Average Return
7
Feb 26, 2026
1,173.2Alien
7
Feb 26, 2026
94.25D4RL Score
7
May 7, 2026
82.2Normalized Score
7
Feb 26, 2026
84Normalized Score
7
Feb 26, 2026
87.8Normalized Score
7
Feb 26, 2026
70.1Normalized Score
7
Feb 26, 2026