Offline Reinforcement Learning on Hopper Medium-Expert JointNoise shift
109.803Performance ScoreQT
Evaluation Results
| Method | Links | |
|---|---|---|
| QTAugmentation Strategy=REAG_MV2024.10 | 109.803 | |
| QTAugmentation Strategy=REAG_Dara2024.10 | 109.746 | |
| ReinformerAugmentation Strategy=REAG_MV2024.10 | 109.472 | |
| DTAugmentation Strategy=REAG_MV2024.10 | 109.367 | |
| ReinformerAugmentation Strategy=1T10S2024.10 | 109.256 | |
| ReinformerAugmentation Strategy=REAG_Dara2024.10 | 109.255 | |
| QTAugmentation Strategy=1T10S2024.10 | 109.056 | |
| DTAugmentation Strategy=REAG_Dara2024.10 | 108.261 | |
| DTAugmentation Strategy=1T10S2024.10 | 108.254 |