Goal-Conditioned Reinforcement Learning (Navigation) on antsoccer-arena-navigate state-based v0 (test)
47Success RateOrig
Evaluation Results
| Method | Links | |
|---|---|---|
| OrigDownstream algorithm=GCIVL, Observation type=State-based2025.10 | 47 | |
| VIBDownstream algorithm=GCIVL, Observation type=State-based2025.10 | 34 | |
| Dual Goal RepresentationsDownstream algorithm=GCIVL, Observation type=State-based2025.10 | 31 | |
| BYOL-γDownstream algorithm=GCIVL, Observation type=State-based2025.10 | 11 | |
| TRADownstream algorithm=GCIVL, Observation type=State-based2025.10 | 8 | |
| VIPDownstream algorithm=GCIVL, Observation type=State-based2025.10 | 2 |