Goal-Conditioned Reinforcement Learning (Navigation) on antmaze-large-navigate state-based v0 (test)
28Success RateDual Goal Representations
Evaluation Results
| Method | Links | |
|---|---|---|
| Dual Goal RepresentationsDownstream algorithm=GCIVL, Observation type=State-based2025.10 | 28 | |
| TRADownstream algorithm=GCIVL, Observation type=State-based2025.10 | 22 | |
| OrigDownstream algorithm=GCIVL, Observation type=State-based2025.10 | 16 | |
| BYOL-γDownstream algorithm=GCIVL, Observation type=State-based2025.10 | 11 | |
| VIBDownstream algorithm=GCIVL, Observation type=State-based2025.10 | 9 | |
| VIPDownstream algorithm=GCIVL, Observation type=State-based2025.10 | 9 |