Offline Reinforcement Learning on Walker2D JointNoise Shift (Medium)
80.904Average ReturnREAG*MV
Evaluation Results
| Method | Links | |
|---|---|---|
| REAG*MVFramework=QT2024.10 | 80.904 | |
| 1T10SFramework=QT2024.10 | 80.621 | |
| REAG*DaraFramework=QT2024.10 | 78.672 | |
| REAG*MVFramework=DT2024.10 | 75.008 | |
| REAG*MVFramework=Reinformer2024.10 | 75.008 | |
| 1T10SFramework=Reinformer2024.10 | 74.748 | |
| REAG*DaraFramework=Reinformer2024.10 | 74.268 | |
| REAG*DaraFramework=DT2024.10 | 71.779 | |
| 1T10SFramework=DT2024.10 | 71.068 |