Offline Reinforcement Learning on Battle N=1000 (Mixed)
67.5Normalized ReturnMF-Diffuser
Evaluation Results
| Method | Links | |
|---|---|---|
| MF-DiffuserN=10002026.05 | 67.5 | |
| MF-CDMs-RLN=10002026.05 | 58.9 | |
| OryxN=10002026.05 | 55.4 | |
| MFQ-OfflineN=10002026.05 | 50.8 | |
| MA-TD3+BCN=10002026.05 | 45.8 | |
| DoFN=10002026.05 | 43 | |
| OMARN=10002026.05 | 41.5 | |
| Indep. DiffuserN=10002026.05 | 39.5 | |
| MADiffN=10002026.05 | 32.1 | |
| Joint DiffuserN=10002026.05 | 27.2 |