Game Level Generation from Gameplay Videos

• DOI: 10.1609/aiide.v12i1.12861
• Publication Date: 2022-10-18T06:24:35Z
• Authors: Matthew Guzdial; Mark Riedl
• Keywords: Video game

We present an unsupervised process to generate full video game levels from a model trained on gameplay video. The represents probabilistic relationships between shapes properties, and relates the stylistic variance within domain. utilize classic platformer Super Mario Bros. evaluate this due its highly-regarded level design. output in comparison other data-driven generation techniques via user study demonstrate ability produce novel more stylistically similar exemplar input.