Policy Generalization
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
-23.36Average Return
6
Feb 26, 2026
-50.86Average Return
6
Feb 26, 2026
968.8Average Return
6
Feb 26, 2026
-5.21Average Return
6
Feb 26, 2026
100,000Win Rate
4
Feb 26, 2026
1.16Average Sum of Scores
4
Feb 26, 2026
115Average Score
4
Feb 26, 2026
1.31Avg Sum Score
4
Feb 26, 2026
32,190Win Rate
3
Feb 26, 2026
4,512Win Rate
3
Feb 26, 2026
-27.86Average Return
3
Feb 26, 2026
-28.61Average Return
3
Feb 26, 2026
—
—Primary metric
0
Feb 26, 2026