Offline Reinforcement Learning on Gaussian Squeeze N=1000 (Mixed)
75.1Normalized ReturnMF-Diffuser
Evaluation results
| Method | Links | |
|---|---|---|
| MF-DiffuserN=10002026.05 | 75.1 | |
| MF-CDMs-RLN=10002026.05 | 69.8 | |
| OryxN=10002026.05 | 67.2 | |
| MFQ-OfflineN=10002026.05 | 61.5 | |
| MADiffN=10002026.05 | 42.3 | |
| DoFN=10002026.05 | 42 | |
| Joint DiffuserN=10002026.05 | 38.1 | |
| Indep. DiffuserN=10002026.05 | 36.7 | |
| MA-TD3+BCN=10002026.05 | 34.5 | |
| OMARN=10002026.05 | 31.8 |