Multi-agent Multi-objective Reinforcement Learning on MPE
11,080.9224HypervolumeMO-MIX
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| MO-MIX2026.02 | 11,080.9224 | 40.4 | 4.2273 | 43.6463 | |
| Outer-loop QMIXbaseline_version=v22026.02 | 9,791.7632 | 21 | 12.2401 | 236.0842 | |
| Outer-loop QMIXbaseline_version=v12026.02 | 9,448.338 | 17 | 15.8387 | 467.3278 |