Offline Reinforcement Learning on Hopper Medium-Replay BodyMass shift
82.786Performance ScoreQT
Evaluation Results
| Method | Links | |
|---|---|---|
| QTAugmentation Strategy=REAG_Dara2024.10 | 82.786 | |
| QTAugmentation Strategy=REAG_MV2024.10 | 76.287 | |
| QTAugmentation Strategy=1T10S2024.10 | 69.46 | |
| DTAugmentation Strategy=REAG_MV2024.10 | 66.092 | |
| DTAugmentation Strategy=1T10S2024.10 | 64.216 | |
| DTAugmentation Strategy=REAG_Dara2024.10 | 60.393 | |
| ReinformerAugmentation Strategy=REAG_Dara2024.10 | 27.238 | |
| ReinformerAugmentation Strategy=REAG_MV2024.10 | 20.952 | |
| ReinformerAugmentation Strategy=1T10S2024.10 | 17.534 |