Offline Reinforcement Learning on Robomimic Lift multi-human
91Avg Normalized ScoreMR
Evaluation results
| Method | Links | |
|---|---|---|
| MROracle status=false, Implementation source=Kim et al. [28]2023.05 | 91 | |
| LSTMOracle status=false, Implementation source=Kim et al. [28]2023.05 | 90.8 | |
| MROracle status=false, Implementation source=reimpl.2023.05 | 90.04 | |
| IPLOracle status=false, Implementation source=Ours2023.05 | 87.2 | |
| IQLOracle status=true, Implementation source=Kim et al. [28]2023.05 | 86.75 | |
| PTOracle status=false, Implementation source=Kim et al. [28]2023.05 | 86.75 | |
| BREXOracle status=false, Implementation source=reimpl.2023.05 | 60.4 |