Offline Reinforcement Learning on Robomimic Lift (proficient-human)
98.84Avg Normalized ScoreMR
Evaluation Results
| Method | Links | |
|---|---|---|
| MROracle status=false, Implementation source=reimpl.2023.05 | 98.84 | |
| IPLOracle status=false, Implementation source=Ours2023.05 | 97.6 | |
| IQLOracle status=true, Implementation source=Kim et al. [28]2023.05 | 96.75 | |
| BREXOracle status=false, Implementation source=reimpl.2023.05 | 96.6 | |
| PTOracle status=false, Implementation source=Kim et al. [28]2023.05 | 91.75 | |
| LSTMOracle status=false, Implementation source=Kim et al. [28]2023.05 | 91.5 | |
| MROracle status=false, Implementation source=Kim et al. [28]2023.05 | 84.75 |