Offline Reinforcement Learning on Hopper Medium-Expert 1T10S
109.803Average ReturnREAG*MV
Evaluation Results
| Method | Links | |
|---|---|---|
| REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=QT2024.10 | 109.803 | |
| REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=QT2024.10 | 109.746 | |
| REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.10 | 109.472 | |
| REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=DT2024.10 | 109.367 | |
| ReinformerDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.10 | 109.256 | |
| REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.10 | 109.255 | |
| QTDistribution Shift=JointNoise (JN), Base Architecture=QT2024.10 | 109.056 | |
| REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=DT2024.10 | 108.261 | |
| DTDistribution Shift=JointNoise (JN), Base Architecture=DT2024.10 | 108.254 | |
| REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=QT2024.10 | 77.279 | |
| REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=QT2024.10 | 73.952 | |
| REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.10 | 73.363 | |
| ReinformerDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.10 | 68.973 | |
| REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.10 | 64.206 | |
| QTDistribution Shift=BodyMass (BM), Base Architecture=QT2024.10 | 61.162 | |
| REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=DT2024.10 | 52.873 | |
| REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=DT2024.10 | 33.631 | |
| DTDistribution Shift=BodyMass (BM), Base Architecture=DT2024.10 | 33.554 |