Multi-agent Offline Reinforcement Learning
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
135.2Score
16
Mar 31, 2026
125.6Score
16
Mar 31, 2026
86.3Score
16
Mar 31, 2026
87.3Score
16
Mar 31, 2026
92.8Score
16
Mar 31, 2026
136.4Score
16
Mar 31, 2026
85.1Score
16
Mar 31, 2026
95.4Score
16
Mar 31, 2026
88.3Score
16
Mar 31, 2026
4,554.11Performance
9
May 29, 2026
0.938Score
8
Feb 26, 2026
73.4Score
8
Mar 31, 2026
68Score
8
Feb 26, 2026
1,875.51Performance Score
3
Apr 28, 2026
2,713.69Return
3
Apr 28, 2026
7,208.19Return
3
Apr 28, 2026
6,925.02Return
3
Apr 28, 2026