Offline Multi-Agent Reinforcement Learning on Multi-agent MuJoCo Swimmer (e, m1, m2, e-m1, e-m2, m1-m2)
430.7ReturnOMIGA
Evaluation results
| Method | Links | |
|---|---|---|
| OMIGADataset Quality=expert, Observability=Partial observable2025.01 | 430.7 | |
| FACMAC+B3CDataset Quality=expert, Observability=Partial observable2025.01 | 430.3 | |
| FACMAC+B3CDataset Quality=expert-medium1, Observability=Partial observable2025.01 | 297.1 | |
| TD3+B3CDataset Quality=medium1, Observability=Partial observable2025.01 | 297 | |
| FACMAC+B3CDataset Quality=medium2, Observability=Partial observable2025.01 | 155.3 |