Continuous Control
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
181.85Run Score
4
Mar 18, 2026
918.29Stand Score
4
Mar 18, 2026
0.83Average Reward
4
Mar 6, 2026
0.94Average Reward
4
Mar 6, 2026
0.62Average Reward
4
Mar 6, 2026
0.56Average Reward
4
Mar 6, 2026
0.51Average Reward
4
Mar 6, 2026
0.79Average Reward
4
Mar 6, 2026
0.56Average Reward
4
Mar 6, 2026
0.92Average Reward
4
Mar 6, 2026
0.71Average Reward
4
Mar 6, 2026
5,701.2Average Return
4
Feb 26, 2026
4,417Average Return
4
Feb 26, 2026
6,466.4Average Return
4
Feb 26, 2026
5,867Average Return
4
Feb 26, 2026
11.43Training Time (h)
4
Feb 26, 2026
5.72Time (h)
4
Feb 26, 2026
3.43Time (h)
4
Feb 26, 2026
908,000QD Score
4
Feb 26, 2026
864,000QD Score
4
Feb 26, 2026
2,273,000QD Score
4
Feb 26, 2026
806.21Cartpole Swingup IQM
4
Feb 26, 2026
656.43Episode Reward
4
Feb 26, 2026
558.23Episode Reward
4
Feb 26, 2026
673.74Episode Reward
4
Feb 26, 2026