Offline Reinforcement Learning on HalfCheetah JointNoise Shift (Medium-Expert)
83.692Average ReturnREAG*MV
Evaluation Results
| Method | Links | |
|---|---|---|
| REAG*MVFramework=QT2024.10 | 83.692 | |
| 1T10SFramework=QT2024.10 | 82.961 | |
| REAG*DaraFramework=QT2024.10 | 82.148 | |
| REAG*MVFramework=Reinformer2024.10 | 79.39 | |
| REAG*DaraFramework=Reinformer2024.10 | 78.981 | |
| REAG*MVFramework=DT2024.10 | 77.762 | |
| REAG*DaraFramework=DT2024.10 | 77.751 | |
| 1T10SFramework=Reinformer2024.10 | 76.073 | |
| 1T10SFramework=DT2024.10 | 70.573 |