Multi-Agent Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
11.1Averaged Score
6
Feb 26, 2026
19.17Averaged Score
6
Feb 26, 2026
19.45Average Score
6
Feb 26, 2026
16.5Averaged Score
6
Feb 26, 2026
19.65Averaged Score
6
Feb 26, 2026
16Average Score
6
Feb 26, 2026
63.35MMM2 7m2M1M vs 8m4M1M Result
6
Feb 26, 2026
20.9Average Score
6
Feb 26, 2026
18.96Test Return
6
Feb 26, 2026
20.45Test Return
6
Feb 26, 2026
89Test Win Rate
5
Jul 7, 2026
14.61Mean Return
5
Jun 30, 2026
13.98Mean Return
5
Jun 30, 2026
15.23Mean Return
5
Jun 30, 2026
14.33Mean Return
5
Jun 30, 2026
17.03Mean Return
5
Jun 30, 2026
14.9Reward
5
Jun 30, 2026
17.9Reward
5
Jun 30, 2026
17.8Reward
5
Jun 30, 2026
1,354.49Average Episode Return
5
Jun 23, 2026
1,546.51Average Episode Return
5
Jun 23, 2026
1,847.32Average Episode Return
5
Jun 23, 2026
2,024.66Average Episode Return
5
Jun 23, 2026
1,586.6Episode Return
5
Jun 23, 2026
-4.227Coin Return
5
May 29, 2026