Offline Reinforcement Learning on Hopper Medium BodyMass Shift
82.786Average ReturnREAG*Dara
Evaluation Results
| Method | Links | |
|---|---|---|
| REAG*DaraFramework=QT2024.10 | 82.786 | |
| REAG*MVFramework=QT2024.10 | 76.287 | |
| 1T10SFramework=QT2024.10 | 69.46 | |
| REAG*MVFramework=DT2024.10 | 66.092 | |
| 1T10SFramework=DT2024.10 | 64.216 | |
| REAG*DaraFramework=QT2024.10 | 62.262 | |
| QTAugmentation Strategy=REAG_Dara2024.10 | 62.262 | |
| REAG*DaraFramework=DT2024.10 | 60.393 | |
| REAG*MVFramework=Reinformer2024.10 | 59.085 | |
| ReinformerAugmentation Strategy=REAG_MV2024.10 | 59.085 | |
| REAG*MVFramework=QT2024.10 | 51.796 | |
| QTAugmentation Strategy=REAG_MV2024.10 | 51.796 | |
| REAG*DaraFramework=Reinformer2024.10 | 51.771 | |
| ReinformerAugmentation Strategy=REAG_Dara2024.10 | 51.771 | |
| 1T10SFramework=Reinformer2024.10 | 51.357 | |
| ReinformerAugmentation Strategy=1T10S2024.10 | 51.357 | |
| 1T10SFramework=QT2024.10 | 49.516 | |
| QTAugmentation Strategy=1T10S2024.10 | 49.516 | |
| REAG*MVFramework=DT2024.10 | 39.435 | |
| DTAugmentation Strategy=REAG_MV2024.10 | 39.435 | |
| REAG*DaraFramework=DT2024.10 | 37.787 | |
| DTAugmentation Strategy=REAG_Dara2024.10 | 37.787 | |
| 1T10SFramework=DT2024.10 | 34.057 | |
| DTAugmentation Strategy=1T10S2024.10 | 34.057 | |
| REAG*DaraFramework=Reinformer2024.10 | 27.238 | |
| REAG*MVFramework=Reinformer2024.10 | 20.952 | |
| 1T10SFramework=Reinformer2024.10 | 17.534 |