Offline Reinforcement Learning on HalfCheetah Medium-Expert JointNoise shift
83.692Performance ScoreQT
Evaluation Results
| Method | Links | |
|---|---|---|
| QTAugmentation Strategy=REAG_MV2024.10 | 83.692 | |
| QTAugmentation Strategy=1T10S2024.10 | 82.961 | |
| QTAugmentation Strategy=REAG_Dara2024.10 | 82.148 | |
| ReinformerAugmentation Strategy=REAG_MV2024.10 | 79.39 | |
| ReinformerAugmentation Strategy=REAG_Dara2024.10 | 78.981 | |
| DTAugmentation Strategy=REAG_MV2024.10 | 77.762 | |
| DTAugmentation Strategy=REAG_Dara2024.10 | 77.751 | |
| ReinformerAugmentation Strategy=1T10S2024.10 | 76.073 | |
| DTAugmentation Strategy=1T10S2024.10 | 70.573 |