Offline Reinforcement Learning on Gaussian Squeeze N=1000 (Medium-Replay)
79.2Normalized ReturnMF-Diffuser
Evaluation results
| Method | Links | |
|---|---|---|
| MF-DiffuserN=10002026.05 | 79.2 | |
| MF-CDMs-RLN=10002026.05 | 74.5 | |
| OryxN=10002026.05 | 71.8 | |
| MFQ-OfflineN=10002026.05 | 66.2 | |
| MADiffN=10002026.05 | 47.5 | |
| DoFN=10002026.05 | 47.1 | |
| Joint DiffuserN=10002026.05 | 42.8 | |
| Indep. DiffuserN=10002026.05 | 41.2 | |
| MA-TD3+BCN=10002026.05 | 39.2 | |
| OMARN=10002026.05 | 36.1 |