Goal-Conditioned Reinforcement Learning on Humanoidmaze large-stitch v0
72Success RateLAVL
Evaluation results
| Method | Links | |
|---|---|---|
| LAVLArchitecture=Hierarchical2026.05 | 72 | |
| OTAArchitecture=Hierarchical2026.05 | 57 | |
| HIQLArchitecture=Hierarchical2026.05 | 28 | |
| CGCIVLArchitecture=Hierarchical2026.05 | 20 | |
| GCBCArchitecture=Non-hierarchical2026.05 | 6 | |
| CRLArchitecture=Non-hierarchical2026.05 | 4 | |
| QRLArchitecture=Non-hierarchical2026.05 | 3 | |
| GCIVLArchitecture=Non-hierarchical2026.05 | 1 | |
| GCIQLArchitecture=Non-hierarchical2026.05 | 0 |