Cooperative Multi-Agent Reinforcement Learning
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
-40.5Best Checkpoint Reward
18
Feb 26, 2026
-0.36Mean Episodic Reward
13
May 12, 2026
85.04Mean Episodic Reward
13
May 12, 2026
-17.22Mean Episodic Reward
13
May 12, 2026
50Mean Episodic Reward
13
May 12, 2026
-25.39Mean Episodic Reward
13
May 12, 2026
73.3Normalized Episodic Returns
12
Feb 26, 2026
91.6Normalized Episodic Return
12
Feb 26, 2026
18.7Return
11
Apr 10, 2026
19.1Return
11
Apr 10, 2026
17.8Return
11
Apr 10, 2026
19.8Return
11
Apr 10, 2026
63Mean Success Rate
6
Feb 26, 2026
0.67Mean Success Rate
6
Feb 26, 2026
21Mean Success Rate
6
Feb 26, 2026
98Mean Success Rate
6
Feb 26, 2026
0.24Mean Success Rate
6
Feb 26, 2026
47Mean Success Rate
6
Feb 26, 2026
91.24Reward
5
Jun 11, 2026
35.43Mean Reward
4
May 26, 2026
43.65Mean Reward
4
May 26, 2026
97.35Mean Reward
4
May 26, 2026
124.39Mean Reward
4
May 26, 2026
148.76Mean Reward
4
May 26, 2026
40FComm
4
May 20, 2026