Abstract. Feature selection in reinforcement learning (RL), i.e. choosing basis functions such that useful approximations of the unkown value function can be obtained, is one of th...
In classical network flow theory the choice of paths, on which flow is sent, is only restricted by arc capacities. This, however, is not realistic in most applications. Many prob...
Annals and chronicles may be the foundation of accounting, but writers of stories and histories have long known that they seldom render a satisfactory account of complex events. I...
While weblogs have been conceptualised as personal thinking spaces since their early days, those uses have not been studied in detail. The purpose of this paper is to explore how ...
One of the major issues for user assistance systems consists of “providing help at an appropriate level”. In this paper we analyze the problem of modeling task experience — ...