Offline Reinforcement Learning on Walker2D Medium JointNoise Shift
80.904Performance ScoreQT
Evaluation Results
| Method | Links | |
|---|---|---|
| QTAugmentation Strategy=REAG_MV2024.10 | 80.904 | |
| QTAugmentation Strategy=1T10S2024.10 | 80.621 | |
| QTAugmentation Strategy=REAG_Dara2024.10 | 78.672 | |
| DTAugmentation Strategy=REAG_MV2024.10 | 75.008 | |
| ReinformerAugmentation Strategy=REAG_MV2024.10 | 75.008 | |
| ReinformerAugmentation Strategy=1T10S2024.10 | 74.748 | |
| ReinformerAugmentation Strategy=REAG_Dara2024.10 | 74.268 | |
| DTAugmentation Strategy=REAG_Dara2024.10 | 71.779 | |
| DTAugmentation Strategy=1T10S2024.10 | 71.068 |