Multi-Agent Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
8,347Average Score
12
Feb 26, 2026
4,373Average Evaluation Score
12
Feb 26, 2026
6,054Average Evaluation Score
12
Feb 26, 2026
7,460Avg Score
12
Feb 26, 2026
7,176Average Return
12
Feb 26, 2026
5,646Average Score
12
Feb 26, 2026
125Mean Episodic Reward (q=2)
12
Feb 26, 2026
144Mean Episodic Reward (q=3)
12
Feb 26, 2026
20Average Score
12
Feb 26, 2026
19.4Average Score
12
Feb 26, 2026
1,798.05Average Episode Reward
11
Jun 23, 2026
1,822.72Average Episode Reward
11
Jun 23, 2026
2,002Average Episode Reward
11
Jun 23, 2026
3,360Average Episode Reward
11
Jun 23, 2026
4,695Average Episode Reward
11
Jun 23, 2026
4,582Avg Episode Reward
11
Jun 23, 2026
5,237Average Episode Reward
11
Jun 23, 2026
5,545Average Episode Reward
11
Jun 23, 2026
19.1Return
11
Apr 10, 2026
-46Return
11
Apr 10, 2026
69Mean Win Rate
10
Jun 30, 2026
0.89Reward
10
Jun 30, 2026
17.4Protoss Reward
10
Jun 30, 2026
2,110Reward
10
Jun 30, 2026
337.8Average Normalized Score
10
Jun 11, 2026