Goal-Conditioned Reinforcement Learning on Cube single-play v0
83Success RateLAVL
Evaluation results
| Method | Links | |
|---|---|---|
| LAVLArchitecture=Hierarchical2026.05 | 83 | |
| GCIQLArchitecture=Non-hierarchical2026.05 | 68 | |
| GCIVLArchitecture=Non-hierarchical2026.05 | 53 | |
| CGCIVLArchitecture=Hierarchical2026.05 | 23 | |
| CRLArchitecture=Non-hierarchical2026.05 | 19 | |
| HIQLArchitecture=Hierarchical2026.05 | 15 | |
| OTAArchitecture=Hierarchical2026.05 | 9 | |
| GCBCArchitecture=Non-hierarchical2026.05 | 6 | |
| QRLArchitecture=Non-hierarchical2026.05 | 5 |