Continuous Control
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
63AUC (200K steps)
3
Jun 16, 2026
358AUC (200K Steps)
3
Jun 16, 2026
257AUC (200K steps)
3
Jun 16, 2026
593AUC (200K steps)
3
Jun 16, 2026
1.33Training Time (s)
3
Jun 5, 2026
0.1Training Time (s)
3
Jun 5, 2026
2.96Best Test Reward
3
Jun 5, 2026
-2.54Best Test Reward
3
Jun 5, 2026
-172Best Test Reward
3
Jun 5, 2026
8.23Best Test Reward
3
Jun 5, 2026
-4.21Best Test Reward
3
Jun 5, 2026
-12.4Best Test Reward
3
Jun 5, 2026
1.81Best Test Reward
3
Jun 5, 2026
-0.438Best Reward
3
Jun 5, 2026
-0.331Best Test Reward
3
Jun 5, 2026
3.8acrobot-swingup
3
Feb 26, 2026
15CT (Time)
3
Feb 26, 2026
0C.V Rate
3
Feb 26, 2026
5.64Action Repetition
3
Feb 26, 2026
0.82Action Repetition
3
Feb 26, 2026
0.021Action Repetition
3
Feb 26, 2026
2.51Action Repetition
3
Feb 26, 2026
95Action Repetition
3
Feb 26, 2026
9.08Action Repetition
3
Feb 26, 2026
7Average Reward
3
Feb 26, 2026