In this paper we consider sampling based fitted value iteration for discounted, large (possibly infinite) state space, finite action Markovian Decision Problems where only a gener...
In this paper we analyze the most popular evaluation metrics for separate-and-conquer rule learning algorithms. Our results show that all commonly used heuristics, including accur...
This paper addresses the development of a computer game design and development curriculum at the authors’ institution. The basis for curriculum decisions, as well as comparison t...
We propose a new rule induction algorithm for solving classification problems via probability estimation. The main advantage of decision rules is their simplicity and good interp...
d Abstract) Richard J. Anderson Paul Beame Walter L. Ruzzo Department of Computer Science and Engineering University of Washingtoni We introduce a task scheduling model which is u...