Goal-Conditioned Reinforcement Learning on Humanoidmaze medium-navigate v0
94Success RateOTA
Evaluation results
| Method | Links | |
|---|---|---|
| OTAArchitecture=Hierarchical2026.05 | 94 | |
| LAVLArchitecture=Hierarchical2026.05 | 94 | |
| HIQLArchitecture=Hierarchical2026.05 | 89 | |
| CGCIVLArchitecture=Hierarchical2026.05 | 88 | |
| CRLArchitecture=Non-hierarchical2026.05 | 60 | |
| GCIQLArchitecture=Non-hierarchical2026.05 | 27 | |
| GCIVLArchitecture=Non-hierarchical2026.05 | 24 | |
| QRLArchitecture=Non-hierarchical2026.05 | 21 | |
| GCBCArchitecture=Non-hierarchical2026.05 | 8 |