Offline Multi-Agent Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
3,621Return
12
Feb 26, 2026
94.3Average Normalized Score
8
Mar 31, 2026
104.9Average Normalized Score
8
Mar 31, 2026
99.4Performance at 3m
8
Mar 13, 2026
43.8Average Normalized Score
7
Mar 31, 2026
73.1Average Normalized Score
7
Mar 31, 2026
81.3Avg Normalized Score
7
Mar 31, 2026
118.5Average Normalized Score
7
Mar 31, 2026
39.7Average Return
6
May 29, 2026
78.9Average Return
6
May 29, 2026
119Average Return
6
May 29, 2026
5.97Mean Performance (N=2)
6
Feb 26, 2026
11.15Mean Performance (N=2)
6
Feb 26, 2026
-1.29Mean Return
6
Feb 26, 2026
-1.27Mean Return
6
Feb 26, 2026
973s5z Win Rate
5
Apr 28, 2026
430.7Return
5
Feb 26, 2026
1,396.8Return
5
Feb 26, 2026
5,413.7Return
5
Feb 26, 2026
2,162.8Return
5
Feb 26, 2026
9.7Average Score
5
Feb 26, 2026
14.02Average Score
5
Feb 26, 2026
13.01Average Score
5
Feb 26, 2026
11.85Average Score
5
Feb 26, 2026
12.05Average Score
5
Feb 26, 2026