User-preference-based automated level generation for platform games

Nick Nygren, Jörg Denzinger, Ben Stephenson, John Aycock

appeared in: Proceedings 2011 IEEE Conference on Computational Intelligence and Games, Seoul, 2011, pp. 55-62.


Level content generation in the genre of platform games, so far, has focused primarily on the typical, tactile-skill based levels with simple left to right movement. In this paper, we present a level generation method that expands these standard kinds of levels by integrating puzzle based content that requires the player to explore the level in order to solve it. With these choices comes the need to elicit what kind of level a user would like to play at the current time, which is also covered by our level generation system.

Download paper (publisher's webpage)

Generated: 30/10/2011