Offline Reinforcement Learning on hopper e-morph
62.9Performance ScoreDROCO
Evaluation Results
| Method | Links | |
|---|---|---|
| DROCOObservation Normalization=false2025.12 | 62.9 | |
| IQLObservation Normalization=false2025.12 | 60.6 | |
| OTDFObservation Normalization=false2025.12 | 53.9 | |
| DROCOObservation Normalization=false2025.12 | 36.5 | |
| IGDFObservation Normalization=false2025.12 | 32.3 | |
| OTDFObservation Normalization=false2025.12 | 31.4 | |
| IGDFObservation Normalization=false2025.12 | 22.7 | |
| IQLObservation Normalization=false2025.12 | 16.7 |