Offline Reinforcement Learning on Hopper Medium-Expert BodyMass Shift
77.279Average ReturnREAG*Dara
Evaluation Results
| Method | Links | |
|---|---|---|
| REAG*DaraFramework=QT2024.10 | 77.279 | |
| QTAugmentation Strategy=REAG_Dara2024.10 | 77.279 | |
| REAG*MVFramework=QT2024.10 | 73.952 | |
| QTAugmentation Strategy=REAG_MV2024.10 | 73.952 | |
| REAG*DaraFramework=Reinformer2024.10 | 73.363 | |
| ReinformerAugmentation Strategy=REAG_Dara2024.10 | 73.363 | |
| 1T10SFramework=Reinformer2024.10 | 68.973 | |
| ReinformerAugmentation Strategy=1T10S2024.10 | 68.973 | |
| REAG*MVFramework=Reinformer2024.10 | 64.206 | |
| ReinformerAugmentation Strategy=REAG_MV2024.10 | 64.206 | |
| 1T10SFramework=QT2024.10 | 61.162 | |
| QTAugmentation Strategy=1T10S2024.10 | 61.162 | |
| REAG*MVFramework=DT2024.10 | 52.873 | |
| DTAugmentation Strategy=REAG_MV2024.10 | 52.873 | |
| REAG*DaraFramework=DT2024.10 | 33.631 | |
| DTAugmentation Strategy=REAG_Dara2024.10 | 33.631 | |
| 1T10SFramework=DT2024.10 | 33.554 | |
| DTAugmentation Strategy=1T10S2024.10 | 33.554 |