Offline Reinforcement Learning on Robomimic Can multi-human
57.6Avg Normalized ScoreIPL
Evaluation Results
| Method | Links | |
|---|---|---|
| IPLOracle status=false, Implementation source=Ours2023.05 | 57.6 | |
| IQLOracle status=true, Implementation source=Kim et al. [28]2023.05 | 56.25 | |
| MROracle status=false, Implementation source=reimpl.2023.05 | 53.6 | |
| PTOracle status=false, Implementation source=Kim et al. [28]2023.05 | 50.5 | |
| MROracle status=false, Implementation source=Kim et al. [28]2023.05 | 47.5 | |
| LSTMOracle status=false, Implementation source=Kim et al. [28]2023.05 | 30.5 | |
| BREXOracle status=false, Implementation source=reimpl.2023.05 | 30.4 |