Cooperative Multi-Agent Reinforcement Learning on 310 random 3x3 matrix games
114Count: QTRAN=VDN=QMIXQTRAN-base
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| QTRAN-baseIGM conditions=satisfied, number of games=310, matrix size=3x32019.05 | 114 | 177 | 5 | 14 | |
| VDNnumber of games=310, matrix size=3x32019.05 | 114 | 177 | 5 | 14 | |
| QMIXnumber of games=310, matrix size=3x32019.05 | 114 | 177 | 5 | 14 |