Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
886.6Max Return
6
Feb 26, 2026
924.9Max Average Return
6
Feb 26, 2026
902.5Max Average Return
6
Feb 26, 2026
0.297bigfish
6
Feb 26, 2026
15,133Alien
6
Feb 26, 2026
44.1Mean Train Performance
6
Feb 26, 2026
7.1Mean Train Performance
6
Feb 26, 2026
9.2Mean Train Performance
6
Feb 26, 2026
32.2Mean Train Performance
6
Feb 26, 2026
10Mean Train Performance
6
Feb 26, 2026
7.5Mean Performance (Train)
6
Feb 26, 2026
20.8Mean Train Performance
6
Feb 26, 2026
7,340Score
6
Feb 26, 2026
1,189Mean Human-Normalized Score
6
Feb 26, 2026
175.25Average Reward
6
Feb 26, 2026
170.81Return
6
Feb 26, 2026
567Mean Human-Normalized Score
6
Feb 26, 2026
591.9Mean HNS
6
Feb 26, 2026
6.345Aes
5
Jul 8, 2026
0.6Return
5
Jul 3, 2026
0.78Return
5
Jul 3, 2026
0.96Return
5
Jul 3, 2026
606Mean Score
5
Jun 23, 2026
0.902Mean Episodic Return
5
Jun 23, 2026
0.744Mean Episodic Return
5
Jun 23, 2026