Offline Reinforcement Learning on HalfCheetah BodyMass Shift (Medium-Replay)
42.405Average ReturnREAG*MV
Evaluation results
| Method | Links | |
|---|---|---|
| REAG*MVFramework=QT2024.10 | 42.405 | |
| QTAugmentation Strategy=REAG_MV2024.10 | 42.405 | |
| REAG*DaraFramework=QT2024.10 | 41.359 | |
| QTAugmentation Strategy=REAG_Dara2024.10 | 41.359 | |
| 1T10SFramework=QT2024.10 | 41.3 | |
| QTAugmentation Strategy=1T10S2024.10 | 41.3 | |
| REAG*MVFramework=Reinformer2024.10 | 32.114 | |
| ReinformerAugmentation Strategy=REAG_MV2024.10 | 32.114 | |
| 1T10SFramework=Reinformer2024.10 | 31.584 | |
| ReinformerAugmentation Strategy=1T10S2024.10 | 31.584 | |
| REAG*MVFramework=DT2024.10 | 27.812 | |
| DTAugmentation Strategy=REAG_MV2024.10 | 27.812 | |
| REAG*DaraFramework=Reinformer2024.10 | 26.995 | |
| ReinformerAugmentation Strategy=REAG_Dara2024.10 | 26.995 | |
| REAG*DaraFramework=DT2024.10 | 24.059 | |
| DTAugmentation Strategy=REAG_Dara2024.10 | 24.059 | |
| 1T10SFramework=DT2024.10 | 20.966 | |
| DTAugmentation Strategy=1T10S2024.10 | 20.966 |