Reinforcement Learning
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
94.53Grand Average Return (G)
9
May 22, 2026
25OSR
9
May 13, 2026
46.7OSR
9
May 13, 2026
1Fraction of Teacher Score
9
May 11, 2026
1.1Fraction of Teacher Score
9
May 11, 2026
-104.58Average Normalized Return
9
May 8, 2026
260.6Maximum Return
9
Jun 24, 2026
5.82Training Duration (hours)
9
Mar 17, 2026
18.38Training Time (h)
9
Mar 17, 2026
6,415Sum
9
Mar 17, 2026
91.6Game Score: Boxing
9
Feb 26, 2026
3,473Average Return
9
Feb 26, 2026
9.61Mean Score
9
Feb 26, 2026
52.75Mean Return
9
Feb 26, 2026
52.7Mean Return
9
Feb 26, 2026
1.25Mean Return
9
Feb 26, 2026
967.865Average Episodic Return
9
Mar 10, 2026
2,829Ant BLT P (v0)
9
Feb 26, 2026
7,128Alien Score
9
Feb 26, 2026
91MMER
9
Feb 26, 2026
0.657MMER
9
Feb 26, 2026
82.8MMER
9
Feb 26, 2026
20.7MMER
9
Feb 26, 2026
0.127MMER
9
Feb 26, 2026
0.944GoToDoor-8x8 Success Rate
9
Feb 26, 2026