Proceedings Abstracts of the Twenty-Fifth International Joint Conference on Artificial Intelligence

Computer-Aided Game Design: Doctoral Consortium Research Abstract / 3998
Aaron Isaksen

Artificial intelligence can model and predict how humans will react to game systems. Using models of human-like imperfect play, one can estimate how quantitative changes to a game will impact a player's qualitative experience. I discuss my research to use artificial intelligence to automatically play, analyze, and design certain classes of games. Not only does it generate new content quickly and effectively, this research also provides some insights into why humans find some games more difficult than others, and how player skill measurably improves over time.