Offline Reinforcement Learning on Robomimic Can (proficient-human)
76.4Avg Normalized ScoreMR
Evaluation results
| Method | Links | |
|---|---|---|
| MROracle status=false, Implementation source=reimpl.2023.05 | 76.4 | |
| IPLOracle status=false, Implementation source=Ours2023.05 | 74.8 | |
| IQLOracle status=true, Implementation source=Kim et al. [28]2023.05 | 74.5 | |
| PTOracle status=false, Implementation source=Kim et al. [28]2023.05 | 69.67 | |
| MROracle status=false, Implementation source=Kim et al. [28]2023.05 | 68 | |
| BREXOracle status=false, Implementation source=reimpl.2023.05 | 63 | |
| LSTMOracle status=false, Implementation source=Kim et al. [28]2023.05 | 62 |