1. Making Racing Fun Through Player Modeling and Track Evolution
- Author
-
Togelius, Julian, De Nardi, Renzo, Lucas, Simon M., Yannakakis, Georgios N., and Hallam, John
- Subjects
Computer Science: Machine Learning ,Computer Science: Neural Nets ,Computer Science: Human Computer Interaction ,Machine Learning ,Neural Nets ,Human Computer Interaction - Abstract
This paper addresses the problem of automatically constructing tracks tailor-made to maximize the enjoyment of individual players in a simple car racing game. To this end, some approaches to player modeling are investigated, and a method of using evolutionary algorithms to construct racing tracks is presented. A simple player-dependent metric of entertainment is proposed and used as the fitness function when evolving tracks. We conclude that accurate player modeling poses some significant challenges, but track evolution works well given the right track representation.
- Published
- 2006