Offline Reinforcement Learning on HalfCheetah BodyMass Shift (Medium)
47.303Average ReturnREAG*MV
Evaluation Results
| Method | Links | |
|---|---|---|
| REAG*MVFramework=QT2024.10 | 47.303 | |
| QTAugmentation Strategy=REAG_MV2024.10 | 47.303 | |
| REAG*DaraFramework=QT2024.10 | 46.383 | |
| QTAugmentation Strategy=REAG_Dara2024.10 | 46.383 | |
| 1T10SFramework=QT2024.10 | 44.656 | |
| QTAugmentation Strategy=1T10S2024.10 | 44.656 | |
| REAG*MVFramework=Reinformer2024.10 | 42.451 | |
| ReinformerAugmentation Strategy=REAG_MV2024.10 | 42.451 | |
| REAG*MVFramework=DT2024.10 | 40.25 | |
| DTAugmentation Strategy=REAG_MV2024.10 | 40.25 | |
| 1T10SFramework=DT2024.10 | 39.954 | |
| DTAugmentation Strategy=1T10S2024.10 | 39.954 | |
| REAG*DaraFramework=Reinformer2024.10 | 38.261 | |
| ReinformerAugmentation Strategy=REAG_Dara2024.10 | 38.261 | |
| REAG*DaraFramework=DT2024.10 | 37.599 | |
| DTAugmentation Strategy=REAG_Dara2024.10 | 37.599 | |
| 1T10SFramework=Reinformer2024.10 | 37.353 | |
| ReinformerAugmentation Strategy=1T10S2024.10 | 37.353 |