Continuous Control
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
6,138.2Avg Return
17
Apr 13, 2026
11.6Number of Active Parameters
16
Jun 19, 2026
24,829Acrobot Swingup Score
16
Feb 26, 2026
1.691IQM
15
May 13, 2026
11,239Average Return
15
May 13, 2026
4,054Average Return
15
May 13, 2026
873Cheetah Run
15
May 7, 2026
4,828Ant Score
15
May 7, 2026
7,518.3Average Return
15
May 21, 2026
3,732.5Average Return
15
Apr 13, 2026
298.4Episodic Cumulative Reward
15
Mar 26, 2026
2,133,326Average Reward
15
Feb 26, 2026
5,078.3Action Performance (p_act=0.1)
14
Mar 10, 2026
0.971Average Reward
14
Jul 7, 2026
87.1IQM
14
Mar 13, 2026
100Success Rate (Source)
14
Feb 26, 2026
7,687Maximum Average Return
13
May 4, 2026
5,626Max Average Return
13
May 4, 2026
12,332.38Max Return
13
May 4, 2026
3,475.69Maximum Average Return
13
Apr 13, 2026
5,026.85Max Return
13
Apr 13, 2026
5,906.7Average Return
13
Apr 13, 2026
836Reward
13
May 7, 2026
6,969.74Average Reward
13
Mar 10, 2026
867Reward
12
May 20, 2026