Offline Reinforcement Learning on Ising Model N=1000 (Mixed)
79.3Normalized ReturnMF-Diffuser
Evaluation results
| Method | Links | |
|---|---|---|
| MF-DiffuserN=10002026.05 | 79.3 | |
| MF-CDMs-RLN=10002026.05 | 76.8 | |
| MFQ-OfflineN=10002026.05 | 75.4 | |
| OryxN=10002026.05 | 73.5 | |
| DoFN=10002026.05 | 69.4 | |
| Indep. DiffuserN=10002026.05 | 66.1 | |
| MADiffN=10002026.05 | 55 | |
| Joint DiffuserN=10002026.05 | 49.5 | |
| OMARN=10002026.05 | 43.3 | |
| MA-TD3+BCN=10002026.05 | 42.1 |