Goal-Conditioned Reinforcement Learning on Humanoidmaze medium-stitch v0
93Success RateLAVL
Evaluation results
| Method | Links | |
|---|---|---|
| LAVLArchitecture=Hierarchical2026.05 | 93 | |
| CGCIVLArchitecture=Hierarchical2026.05 | 89 | |
| HIQLArchitecture=Hierarchical2026.05 | 88 | |
| OTAArchitecture=Hierarchical2026.05 | 88 | |
| CRLArchitecture=Non-hierarchical2026.05 | 36 | |
| GCBCArchitecture=Non-hierarchical2026.05 | 29 | |
| QRLArchitecture=Non-hierarchical2026.05 | 18 | |
| GCIVLArchitecture=Non-hierarchical2026.05 | 12 | |
| GCIQLArchitecture=Non-hierarchical2026.05 | 12 |