Offline Reinforcement Learning on Gaussian Squeeze Medium N=1000
83.5Normalized ReturnMF-Diffuser
Evaluation results
| Method | Links | |
|---|---|---|
| MF-DiffuserN=10002026.05 | 83.5 | |
| MF-CDMs-RLN=10002026.05 | 79.2 | |
| OryxN=10002026.05 | 76.5 | |
| MFQ-OfflineN=10002026.05 | 71.6 | |
| MADiffN=10002026.05 | 54 | |
| DoFN=10002026.05 | 52.8 | |
| Joint DiffuserN=10002026.05 | 49.2 | |
| Indep. DiffuserN=10002026.05 | 46.3 | |
| MA-TD3+BCN=10002026.05 | 44.7 | |
| OMARN=10002026.05 | 41.3 |