Goal-Conditioned Reinforcement Learning (Manipulation) on puzzle-4x4-play state-based v0 (test)
23Success RateDual Goal Representations
Evaluation Results
| Method | Links | |
|---|---|---|
| Dual Goal RepresentationsDownstream algorithm=GCIVL, Observation type=State-based2025.10 | 23 | |
| OrigDownstream algorithm=GCIVL, Observation type=State-based2025.10 | 14 | |
| TRADownstream algorithm=GCIVL, Observation type=State-based2025.10 | 10 | |
| VIBDownstream algorithm=GCIVL, Observation type=State-based2025.10 | 6 | |
| VIPDownstream algorithm=GCIVL, Observation type=State-based2025.10 | 1 | |
| BYOL-γDownstream algorithm=GCIVL, Observation type=State-based2025.10 | 1 |