Offline Reinforcement Learning on Battle N=1000 (Expert)
84.2Normalized ReturnMF-Diffuser
Evaluation Results
| Method | Links | |
|---|---|---|
| MF-DiffuserN=10002026.05 | 84.2 | |
| MF-CDMs-RLN=10002026.05 | 78.6 | |
| OryxN=10002026.05 | 76.3 | |
| MFQ-OfflineN=10002026.05 | 72.3 | |
| MA-TD3+BCN=10002026.05 | 70.1 | |
| OMARN=10002026.05 | 66.8 | |
| DoFN=10002026.05 | 65.8 | |
| Indep. DiffuserN=10002026.05 | 61.4 | |
| MADiffN=10002026.05 | 58.4 | |
| Joint DiffuserN=10002026.05 | 52.1 |