Offline Reinforcement Learning on Battle N=1000 (Medium)
75.8Normalized Return (%)MF-Diffuser
Evaluation results
| Method | Links | |
|---|---|---|
| MF-DiffuserN=10002026.05 | 75.8 | |
| MF-CDMs-RLN=10002026.05 | 68.4 | |
| OryxN=10002026.05 | 65.4 | |
| MFQ-OfflineN=10002026.05 | 62.1 | |
| MA-TD3+BCN=10002026.05 | 57.5 | |
| DoFN=10002026.05 | 54.1 | |
| OMARN=10002026.05 | 52.4 | |
| Indep. DiffuserN=10002026.05 | 49.8 | |
| MADiffN=10002026.05 | 42.4 | |
| Joint DiffuserN=10002026.05 | 37.6 |