Goal-Conditioned Reinforcement Learning on Antmaze large-stitch v0
92Success RateLAVL
Evaluation results
| Method | Links | |
|---|---|---|
| LAVLArchitecture=Hierarchical2026.05 | 92 | |
| OTAArchitecture=Hierarchical2026.05 | 84 | |
| CGCIVLArchitecture=Hierarchical2026.05 | 81 | |
| HIQLArchitecture=Hierarchical2026.05 | 67 | |
| GCIVLArchitecture=Non-hierarchical2026.05 | 18 | |
| QRLArchitecture=Non-hierarchical2026.05 | 18 | |
| CRLArchitecture=Non-hierarchical2026.05 | 11 | |
| GCIQLArchitecture=Non-hierarchical2026.05 | 7 | |
| GCBCArchitecture=Non-hierarchical2026.05 | 3 |