Goal-Conditioned Reinforcement Learning on AntMaze Medium Navigate (state-based v0, test)
75Success RateDual Goal Representations
Evaluation Results
| Method | Links | |
|---|---|---|
| Dual Goal RepresentationsDownstream algorithm=GCIVL, Observation type=State-based2025.10 | 75 | |
| OrigDownstream algorithm=GCIVL, Observation type=State-based2025.10 | 71 | |
| VIBDownstream algorithm=GCIVL, Observation type=State-based2025.10 | 68 | |
| BYOL-γDownstream algorithm=GCIVL, Observation type=State-based2025.10 | 39 | |
| VIPDownstream algorithm=GCIVL, Observation type=State-based2025.10 | 31 | |
| TRADownstream algorithm=GCIVL, Observation type=State-based2025.10 | 22 |