Offline Reinforcement Learning on half-me-kinematic MuJoCo
51.3Normalized ScoreDROCO
Evaluation results
| Method | Links | |
|---|---|---|
| DROCOObservation Normalization=true, Observation Shift=kinematic2025.12 | 51.3 | |
| OTDFObservation Normalization=true, Observation Shift=kinematic2025.12 | 44.3 | |
| IQLObservation Normalization=true, Observation Shift=kinematic2025.12 | 41.2 | |
| IGDFObservation Normalization=true, Observation Shift=kinematic2025.12 | 35.5 |