Offline Reinforcement Learning on Gaussian Squeeze N=1000 (Expert)
87.1Normalized ReturnMF-CDMs-RL
Evaluation results
| Method | Links | |
|---|---|---|
| MF-CDMs-RLN=10002026.05 | 87.1 | |
| MF-DiffuserN=10002026.05 | 86.3 | |
| OryxN=10002026.05 | 84.8 | |
| MFQ-OfflineN=10002026.05 | 78.4 | |
| MADiffN=10002026.05 | 70.2 | |
| Joint DiffuserN=10002026.05 | 63.5 | |
| DoFN=10002026.05 | 60.9 | |
| MA-TD3+BCN=10002026.05 | 58.6 | |
| Indep. DiffuserN=10002026.05 | 55.8 | |
| OMARN=10002026.05 | 55.2 |