Anisotropic Representations Improve Planning in JEPA World Models
아직 한국어판이 없어 영어 원문으로 표시.
초록 발췌
Latent world models learn action-conditioned dynamics in representation space and often score candidate actions by Euclidean distance to a goal representation. Joint training typically regularizes the representation to prevent collapse, but the resulting representation geometry also determines how terminal errors are weighted during planning.
초록에서 가져왔습니다. 요약을 준비 중입니다.