Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Towards engaging games

 
: Missura, O.; Kersting, K.; Gärtner, T.

:
Volltext urn:nbn:de:0011-n-909473 (192 KByte PDF)
MD5 Fingerprint: eff1e4acc564cf0f98664407c9c2cd85
Erstellt am: 19.3.2009


Baumeister, J.:
LWA 2008, Workshop-Woche: Lernen, Wissen & Adaptivität : Würzburg, 6.-8. Oktober 2008
Würzburg: Univ. Würzburg, 2008 (Universität Würzburg, Institut für Informatik. Technical report 448)
5 S.
Workshop Lernen, Wissensentdeckung und Adaptivität (LWA) <2008, Würzburg>
Workshop on Adaptivity and User Modeling in Iteractive Systems (ABIS) <16, 2008, Würzburg>
Workshop of the Special Interest Group for Information Retrieval (FGIR) <2008, Würzburg>
Workshop on Knowledge Discovery, Data Mining, and Machine Learning (KDML) <2008, Würzburg>
Workshop on Knowledge and Experience Management (FGWM) <2008, Würzburg>
Englisch
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IAIS ()

Abstract
One of the challenges that a computer game developer meets when creating a new game is setting the difficulty ``right''. Not only is it a complicated task to balance all the game parameters, but the developer also needs to cater for players with very different skill levels. Providing a game with an ability to automatically scale the difficulty depending on the current player would make the games more engaging over longer time. While a few commercial games boast about having such a system, to the best of our knowledge treating it as a machine learning problem has received surprisingly low attention. In this paper, we investigate the {\it automatic difficulty scaling problem} from a more general perspective: How can agents learn to keep agents engaged. After introducing the learning problem, called \emph{Engagement Problem}, we outline a framework based on nested Markov Decision Processes, called \emph{Engaging Markov Decision Process}, for solving it. Preliminary experiments in a small grid world show the effectiveness of our approach.

: http://publica.fraunhofer.de/dokumente/N-90947.html