Offline Reinforcement Learning on HalfCheetah JointNoise Shift (Medium)
56.213Average Return1T10S
Evaluation Results
| Method | Links | |
|---|---|---|
| 1T10SFramework=QT2024.10 | 56.213 | |
| QTAugmentation Strategy=1T10S2024.10 | 56.213 | |
| REAG*DaraFramework=QT2024.10 | 55.026 | |
| QTAugmentation Strategy=REAG_Dara2024.10 | 55.026 | |
| REAG*MVFramework=QT2024.10 | 52.394 | |
| QTAugmentation Strategy=REAG_MV2024.10 | 52.394 | |
| REAG*DaraFramework=Reinformer2024.10 | 48.404 | |
| ReinformerAugmentation Strategy=REAG_Dara2024.10 | 48.404 | |
| 1T10SFramework=Reinformer2024.10 | 48.274 | |
| ReinformerAugmentation Strategy=1T10S2024.10 | 48.274 | |
| REAG*DaraFramework=DT2024.10 | 47.833 | |
| DTAugmentation Strategy=REAG_Dara2024.10 | 47.833 | |
| 1T10SFramework=DT2024.10 | 47.725 | |
| DTAugmentation Strategy=1T10S2024.10 | 47.725 | |
| REAG*MVFramework=DT2024.10 | 44.149 | |
| DTAugmentation Strategy=REAG_MV2024.10 | 44.149 | |
| REAG*MVFramework=Reinformer2024.10 | 43.009 | |
| ReinformerAugmentation Strategy=REAG_MV2024.10 | 43.009 |