In August 2010, the first ever Mario level generation competition was held at the Computational Intelligence in Games (CIG) conference. The contest involved generating a personalized level for a particular player, using metrics from a player’s prior playthrough of a different level. There were three entries from the Expressive Intelligence Studio, including the winner, Ben Weber!
However, this competition had only the CIG audience as participants and judges. Julian Togelius and Noor Shaker at ITU Copenhagen have now opened up the competition for the general public to participate. The goal is to gather more (and more detailed) data on the differences between the generated levels and players’ preferences between them. We invite everyone to participate in these experiments!
After all, how often can you play Mario and advance science all at the same time?
About the author: Gillian Smith is a 5th year PhD student researching computer supported level design and procedural content generation. Her other interests include women in games and games in education.