Offline Reinforcement Learning on Walker2D Medium BodyMass Shift
94.578Average ReturnREAG*Dara
Evaluation Results
| Method | Links | |
|---|---|---|
| REAG*DaraFramework=QT2024.10 | 94.578 | |
| 1T10SFramework=QT2024.10 | 93.082 | |
| REAG*MVFramework=QT2024.10 | 92.744 | |
| REAG*MVFramework=DT2024.10 | 88.235 | |
| REAG*DaraFramework=DT2024.10 | 85.328 | |
| REAG*MVFramework=Reinformer2024.10 | 84.897 | |
| REAG*MVFramework=QT2024.10 | 84.582 | |
| QTAugmentation Strategy=REAG_MV2024.10 | 84.582 | |
| 1T10SFramework=DT2024.10 | 84.43 | |
| 1T10SFramework=QT2024.10 | 84.325 | |
| QTAugmentation Strategy=1T10S2024.10 | 84.325 | |
| REAG*DaraFramework=Reinformer2024.10 | 83.761 | |
| 1T10SFramework=Reinformer2024.10 | 83.388 | |
| REAG*DaraFramework=QT2024.10 | 83.068 | |
| QTAugmentation Strategy=REAG_Dara2024.10 | 83.068 | |
| REAG*MVFramework=Reinformer2024.10 | 82.354 | |
| ReinformerAugmentation Strategy=REAG_MV2024.10 | 82.354 | |
| REAG*MVFramework=DT2024.10 | 80.857 | |
| 1T10SFramework=Reinformer2024.10 | 80.857 | |
| DTAugmentation Strategy=REAG_MV2024.10 | 80.857 | |
| ReinformerAugmentation Strategy=1T10S2024.10 | 80.857 | |
| REAG*DaraFramework=Reinformer2024.10 | 80.666 | |
| ReinformerAugmentation Strategy=REAG_Dara2024.10 | 80.666 | |
| 1T10SFramework=DT2024.10 | 78.768 | |
| DTAugmentation Strategy=1T10S2024.10 | 78.768 | |
| REAG*DaraFramework=DT2024.10 | 78.257 | |
| DTAugmentation Strategy=REAG_Dara2024.10 | 78.257 |