Offline Reinforcement Learning on Hopper Medium JointNoise Shift
109.803Average ReturnREAG*MV
Evaluation Results
| Method | Links | |
|---|---|---|
| REAG*MVFramework=QT2024.10 | 109.803 | |
| REAG*DaraFramework=QT2024.10 | 109.746 | |
| REAG*MVFramework=Reinformer2024.10 | 109.472 | |
| REAG*MVFramework=DT2024.10 | 109.367 | |
| 1T10SFramework=Reinformer2024.10 | 109.256 | |
| REAG*DaraFramework=Reinformer2024.10 | 109.255 | |
| 1T10SFramework=QT2024.10 | 109.056 | |
| REAG*DaraFramework=DT2024.10 | 108.261 | |
| 1T10SFramework=DT2024.10 | 108.254 | |
| REAG*DaraFramework=DT2024.10 | 78.325 | |
| DTAugmentation Strategy=REAG_Dara2024.10 | 78.325 | |
| REAG*MVFramework=QT2024.10 | 73.987 | |
| QTAugmentation Strategy=REAG_MV2024.10 | 73.987 | |
| REAG*MVFramework=Reinformer2024.10 | 72.346 | |
| ReinformerAugmentation Strategy=REAG_MV2024.10 | 72.346 | |
| 1T10SFramework=DT2024.10 | 70.685 | |
| DTAugmentation Strategy=1T10S2024.10 | 70.685 | |
| REAG*DaraFramework=Reinformer2024.10 | 70.466 | |
| ReinformerAugmentation Strategy=REAG_Dara2024.10 | 70.466 | |
| REAG*MVFramework=DT2024.10 | 70.356 | |
| DTAugmentation Strategy=REAG_MV2024.10 | 70.356 | |
| 1T10SFramework=Reinformer2024.10 | 70.34 | |
| ReinformerAugmentation Strategy=1T10S2024.10 | 70.34 | |
| REAG*DaraFramework=QT2024.10 | 68.709 | |
| QTAugmentation Strategy=REAG_Dara2024.10 | 68.709 | |
| 1T10SFramework=QT2024.10 | 68.656 | |
| QTAugmentation Strategy=1T10S2024.10 | 68.656 |