Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Towards engaging MDPs

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

Fulltext urn:nbn:de:0011-n-909416 (192 KByte PDF)
MD5 Fingerprint: 30bf79ffa420488324bc1549b9cb46de
Created on: 19.3.2009

Botea, A.; Linares López, C.:
ECAI'08 Workshop on Artificial Intelligence in Games, AIG-08. Working notes : held in conjunction with ECAI 2008. Patras, Greece July 22, 2008
Patras, 2008
5 pp.
European Conference on Artificial Intelligence (ECAI) <18, 2008, Patras>
Workshop on Artificial Intelligence in Games (AIG) <2008, Patras>
Conference Paper, Electronic Publication
Fraunhofer IAIS ()

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 it was not researched as a learning problem. In this paper we first give a problem definition of the automatic difficulty scaling problem we call \emph{Engagement Problem}. Then, we also 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.