Offline Reinforcement Learning on HalfCheetah Medium-Replay JointNoise shift
53.87Performance ScoreQT
Evaluation Results
| Method | Links | |
|---|---|---|
| QTAugmentation Strategy=REAG_MV2024.10 | 53.87 | |
| QTAugmentation Strategy=1T10S2024.10 | 53.763 | |
| QTAugmentation Strategy=REAG_Dara2024.10 | 53.257 | |
| ReinformerAugmentation Strategy=REAG_MV2024.10 | 40.84 | |
| ReinformerAugmentation Strategy=1T10S2024.10 | 40.296 | |
| ReinformerAugmentation Strategy=REAG_Dara2024.10 | 38.436 | |
| DTAugmentation Strategy=REAG_MV2024.10 | 38.417 | |
| DTAugmentation Strategy=REAG_Dara2024.10 | 38.031 | |
| DTAugmentation Strategy=1T10S2024.10 | 36.509 |