The success ofreinforcement learninginpractical problems depends on the ability to combine function approximation with temporal di erence methods such as value iteration. Experime...
The fundamental operation of dominance testing, i.e., determining if one alternative is preferred to another, is in general very hard for methods of reasoning with qualitative cond...
Curves on surfaces play an important role in computer-aided geometric design. Because of the considerably high degree of exact curves on surfaces, approximation algorithms are pre...
Yi-Jun Yang, Song Cao, Jun-Hai Yong, Hui Zhang, Je...
In this paper we introduce “clipping,” a new method of syntactic approximation which is motivated by and works in conjunction with a sound and decidable denotational model for...
Approximate Linear Programming (ALP) is a reinforcement learning technique with nice theoretical properties, but it often performs poorly in practice. We identify some reasons for...