AbstractāIn this paper, we propose a novel propagationbased stereo matching algorithm. Starting from an initial disparity map, our algorithm selects highly reliable pixels and pr...
This paper addresses the task of trajectory cost prediction, a new learning task for trajectories. The goal of this task is to predict the cost for an arbitrary (possibly unknown)...
In this paper we propose differential eligibility vectors (DEV) for temporal-difference (TD) learning, a new class of eligibility vectors designed to bring out the contribution of...
Behind every search query is a high-level mission that the user wants to accomplish. While current search engines can often provide relevant information in response to well-speciļ...
Previous research in Artiļ¬cial Intelligence has identiļ¬ed the possibility of simplifying planning problems via the identiļ¬cation and exploitation of symmetries. We advance t...