dr. Mike Preuss

Pixels, States, and Evolution: What is Hot in Game AI

Recent popular successes in Game AI have shown that computer programs can play almost every game better than almost every human in the world. But how do they do it? And what does that mean for the future of Game AI? What are we dealing with in the near future?

Dr. Preuss' research focuses on the field of evolutionary algorithms for multi-modal and multi-objective optimization, and on computational intelligence and machine learning methods for computer games. In this talk, he will give an overview over the methods that are in approaches like AlphaStar, but also highlight what is going in the other big Game AI areas: Procedural Content Generation and Player Modeling.

Speaker:

dr. Mike Preuss

Mike Preuss is assistant professor at LIACS, the Computer Science department of Leiden University. He works in AI, namely game AI, natural computing, and social media computing.

Mike received his PhD in 2013 from the Chair of Algorithm Engineering at TU Dortmund, Germany, and was with ERCIS at the WWU Muenster, Germany, from 2013 to 2018. His research interests focus on the field of evolutionary algorithms for real-valued problems, namely on multi-modal and multi-objective optimization, and on computational intelligence and machine learning methods for computer games.

Recently, he is also involved in Social Media Computing, and he is publications chair of the upcoming multi-disciplinary MISDOOM conference 2019. He is associate editor of the IEEE Transactions on Games journal and has been member of the organizational team of several conferences in the last years, and notably is general (co-)chair of the PPSN 2020 conference in Leiden.

(PPSN Conference Website)

dr. Preuss's favourite game is Horizon Zero Dawn, and his favourite genre is RTS, with examples such as the Total War series.