PAVE: Predictive Alignment and Value-Guided Evolution for World-Action Policies
技术动态AI 85
来源：arXiv cs.AI发布时间待核实
arXiv:2608.30378v2 Announce Type: replace-cross Abstract: Direct vision-language-action policies generate continuous robot actions efficiently, but standard behavior cloning leaves two complementary gaps: their representations are not explicitly required to describe how the scene evolves over multiple time scales, and deployment trajectories of unequal quality are often reused without separating useful dynamics from undesirable behavior. We introduce \method, a direct world-action policy that co…