Goal-Conditioned Reinforcement Learning on Cube double-play v0
42Success RateLAVL
Evaluation Results
| Method | Links | |
|---|---|---|
| LAVLArchitecture=Hierarchical2026.05 | 42 | |
| GCIQLArchitecture=Non-hierarchical2026.05 | 40 | |
| GCIVLArchitecture=Non-hierarchical2026.05 | 36 | |
| CRLArchitecture=Non-hierarchical2026.05 | 10 | |
| CGCIVLArchitecture=Hierarchical2026.05 | 7 | |
| HIQLArchitecture=Hierarchical2026.05 | 6 | |
| OTAArchitecture=Hierarchical2026.05 | 3 | |
| GCBCArchitecture=Non-hierarchical2026.05 | 1 | |
| QRLArchitecture=Non-hierarchical2026.05 | 1 |