Offline Reinforcement Learning on half-e-kinematic MuJoCo
42.6Normalized ScoreDROCO
Evaluation results
| Method | Links | |
|---|---|---|
| DROCOObservation Normalization=true, Observation Shift=kinematic2025.12 | 42.6 | |
| OTDFObservation Normalization=true, Observation Shift=kinematic2025.12 | 33.8 | |
| IQLObservation Normalization=true, Observation Shift=kinematic2025.12 | 26.5 | |
| IGDFObservation Normalization=true, Observation Shift=kinematic2025.12 | 21.4 |