Rethinking Representations for World-Action Modeling
아직 한국어판이 없어 영어 원문으로 표시.
초록 발췌
World-action models jointly learn robot policies and predict future observations, making the representation space an interface between control and prediction. We study the design of this space through controlled comparisons, finding that neither reconstruction fidelity nor pre-trained perceptual features alone ensure effective policy learning.
초록에서 가져왔습니다. 요약을 준비 중입니다.