Goal-Conditioned Reinforcement Learning on Humanoidmaze large-navigate v0
83Success RateOTA
Evaluation results
| Method | Links | |
|---|---|---|
| OTAArchitecture=Hierarchical2026.05 | 83 | |
| LAVLArchitecture=Hierarchical2026.05 | 74 | |
| HIQLArchitecture=Hierarchical2026.05 | 49 | |
| CGCIVLArchitecture=Hierarchical2026.05 | 46 | |
| CRLArchitecture=Non-hierarchical2026.05 | 24 | |
| QRLArchitecture=Non-hierarchical2026.05 | 5 | |
| GCIVLArchitecture=Non-hierarchical2026.05 | 2 | |
| GCIQLArchitecture=Non-hierarchical2026.05 | 2 | |
| GCBCArchitecture=Non-hierarchical2026.05 | 1 |