Title :
Analyzing player behavior in Pacman using feature-driven decision theoretic predictive modeling
Author :
Cowley, Bill ; Charles, Darryl ; Black, Michaela ; Hickey, Ray
Author_Institution :
Centre for Knowledge & Innovation Res., Helsinki Sch. of Econ., Helsinki, Finland
Abstract :
We describe the results of a modeling methodology that combines the formal choice-system representation of decision theory with a human player-focused description of the behavioral features of game play in Pacman. This predictive player modeler addresses issues raised in previous work and, to produce reliable accuracy. This paper focuses on using player-centric knowledge to reason about player behavior, utilizing a set of features which describe game-play to obtain quantitative data corresponding to qualitative behavioral concepts.
Keywords :
behavioural sciences computing; computer games; decision theory; knowledge representation; Pacman; behavioral feature; decision theory; feature-driven decision theoretic predictive modeling; formal choice-system representation; game play; human player-focused description; player behavior analysis; player-centric knowledge; Data mining; Decision making; Decision theory; Economic forecasting; Game theory; Humans; Predictive models; State estimation; Taxonomy; Technological innovation;
Conference_Titel :
Computational Intelligence and Games, 2009. CIG 2009. IEEE Symposium on
Conference_Location :
Milano
Print_ISBN :
978-1-4244-4814-2
Electronic_ISBN :
978-1-4244-4815-9
DOI :
10.1109/CIG.2009.5286479
