Offline Reinforcement Learning on HalfCheetah JointNoise Shift (Medium-Replay)
53.87Average ReturnREAG*MV
Evaluation Results
| Method | Links | |
|---|---|---|
| REAG*MVFramework=QT2024.10 | 53.87 | |
| 1T10SFramework=QT2024.10 | 53.763 | |
| REAG*DaraFramework=QT2024.10 | 53.257 | |
| REAG*MVFramework=Reinformer2024.10 | 40.84 | |
| 1T10SFramework=Reinformer2024.10 | 40.296 | |
| REAG*DaraFramework=Reinformer2024.10 | 38.436 | |
| REAG*MVFramework=DT2024.10 | 38.417 | |
| REAG*DaraFramework=DT2024.10 | 38.031 | |
| 1T10SFramework=DT2024.10 | 36.509 |