Article Abstract

	Title:	Bayesian imitation learning in game characters
	Author:	Christian Thurau, Tobias Paczian, Gerhard Sagerer, Christian Bauckhage
	Address:	Faculty of Technology, Applied Computer Science, Bielefeld University, P.O. Box 100 131, 33501 Bielefeld, Germany. ' Faculty of Technology, Applied Computer Science, Bielefeld University, P.O. Box 100 131, 33501 Bielefeld, Germany. ' Faculty of Technology, Applied Computer Science, Bielefeld University, P.O. Box 100 131, 33501 Bielefeld, Germany. ' Centre for Vision Research, York University, 4700 Keele St., Toronto, ON, M3J 1P3, Canada
	Journal:	International Journal of Intelligent Systems Technologies and Applications 2007 - Vol. 2, No.2/3  pp. 284 - 295
	Abstract:	Imitation learning is a powerful mechanism applied by primates and humans. It allows for a straightforward acquisition of behaviours that, through observation, are known to solve everyday tasks. Recently, a Bayesian formulation has been proposed that provides a mathematical model of imitation learning. In this paper, we apply this framework to the problem of programming believable computer games characters. We will present experiments in imitation learning from the network traffic of multi-player online games. Our results underline that this indeed produces agents that behave more human-like than characters controlled by common game AI techniques.
	Keywords:	imitation learning; Bayesian learning; behaviour modelling; computer games; games characters; game AI; automatic learning; real time.
	DOI:	10.1504/IJISTA.2007.012489
		Purchase this Paper         Comment on the Paper