AI RESEARCH
STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization
arXiv CS.LG
•
ArXi:2506.03863v3 Announce Type: replace-cross Transforming complex actions into discrete skill abstractions has nstrated strong potential for robotic manipulation. Existing approaches mainly leverage latent variable models, e.g., VQ-VAE, to learn skill abstractions through learned vectors (codebooks), while they suffer from codebook collapse and modeling the causal relationship between learned skills.