Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.97Mean Best Reward
12
Jun 23, 2026
3,312Return
12
May 7, 2026
4,329Return
12
May 7, 2026
5,620Return
12
May 7, 2026
4,260Return
12
May 7, 2026
21,100Return
12
Apr 6, 2026
15.4Return
12
Apr 6, 2026
148Reach Count BL
12
Mar 17, 2026
720Jump Score
12
Mar 17, 2026
729Flip Success Score
12
Mar 17, 2026
128.5Average Episodic Reward
12
May 12, 2026
0.94Reward
12
May 12, 2026
1,725Average Return
12
Feb 26, 2026
982Average Episodic Return
12
Feb 26, 2026
533Average Episodic Return
12
Apr 16, 2026
623Average Episodic Return
12
Apr 16, 2026
3,722.2Average Return
12
Feb 26, 2026
4,788.6Average Return
12
Feb 26, 2026
1,794.4Average Return
12
Feb 26, 2026
-4.1Average Return
12
Feb 26, 2026
5,256Average Performance
12
Feb 26, 2026
129,501Average Performance
12
Feb 26, 2026
2,983Average Performance
12
Feb 26, 2026
7,495Average Performance
12
Feb 26, 2026
8,069Average Performance
12
Feb 26, 2026