Offline Reinforcement Learning on HalfCheetah BodyMass Shift (Medium-Expert)
76.533Average ReturnREAG*Dara
Evaluation Results
| Method | Links | |
|---|---|---|
| REAG*DaraFramework=QT2024.10 | 76.533 | |
| QTAugmentation Strategy=REAG_Dara2024.10 | 76.533 | |
| 1T10SFramework=QT2024.10 | 71.08 | |
| QTAugmentation Strategy=1T10S2024.10 | 71.08 | |
| REAG*MVFramework=QT2024.10 | 69.819 | |
| QTAugmentation Strategy=REAG_MV2024.10 | 69.819 | |
| REAG*MVFramework=DT2024.10 | 56.228 | |
| DTAugmentation Strategy=REAG_MV2024.10 | 56.228 | |
| REAG*DaraFramework=Reinformer2024.10 | 55.818 | |
| ReinformerAugmentation Strategy=REAG_Dara2024.10 | 55.818 | |
| 1T10SFramework=DT2024.10 | 54.981 | |
| DTAugmentation Strategy=1T10S2024.10 | 54.981 | |
| REAG*DaraFramework=DT2024.10 | 51.357 | |
| DTAugmentation Strategy=REAG_Dara2024.10 | 51.357 | |
| REAG*MVFramework=Reinformer2024.10 | 46.048 | |
| ReinformerAugmentation Strategy=REAG_MV2024.10 | 46.048 | |
| 1T10SFramework=Reinformer2024.10 | 40.568 | |
| ReinformerAugmentation Strategy=1T10S2024.10 | 40.568 |