DocumentCode :
2447227
Title :
Predicting player behavior in Tomb Raider: Underworld
Author :
Mahlmann, Tobias ; Drachen, Anders ; Togelius, Julian ; Canossa, Alessandro ; Yannakakis, Georgios N.
Author_Institution :
Center for Comput. Games Res., IT Univ. of Copenhagen, Copenhagen, Denmark
fYear :
2010
fDate :
18-21 Aug. 2010
Firstpage :
178
Lastpage :
185
Abstract :
This paper presents the results of an explorative study on predicting aspects of playing behavior for the major commercial title Tomb Raider: Underworld (TRU). Various supervised learning algorithms are trained on a large-scale set of in-game player behavior data, to predict when a player will stop playing the TRU game and, if the player completes the game, how long will it take to do so. Results reveal that linear regression models and other non-linear classification techniques perform well on the tasks and that decision tree learning induces small yet well-performing and informative trees. Moderate performance is achieved from the prediction models, which indicates the complexity of predicting player behavior based on a constrained set of gameplay metrics and the noise existent in the dataset examined, a generic problem in large-scale data collection from millions of remote clients.
Keywords :
computer games; learning (artificial intelligence); pattern classification; solid modelling; TRU game; Tomb Raider:Underworld; constrained set; decision tree learning; gameplay metrics; generic problem; informative tree; large scale data collection; linear regression model; nonlinear classification technique; player behavior prediction; remote client; supervised learning algorithm; Classification algorithms; Data mining; Feature extraction; Games; Machine learning algorithms; Measurement; Prediction algorithms; Player modeling; Tomb Raider: Underworld; classification; supervised learning;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computational Intelligence and Games (CIG), 2010 IEEE Symposium on
Conference_Location :
Dublin
Print_ISBN :
978-1-4244-6295-7
Electronic_ISBN :
978-1-4244-6296-4
Type :
conf
DOI :
10.1109/ITW.2010.5593355
Filename :
5593355
Link To Document :
بازگشت