Capturing Local and Global Patterns in Procedural Content Generation via Machine Learning
This work addresses a specific challenge in PCGML for game developers, but it is incremental as it builds on existing methods with targeted modifications.
The paper tackled the problem of capturing large-scale visual patterns like symmetry in procedural content generation via machine learning (PCGML), particularly in match-three games, by proposing adaptations to existing methods such as augmenting Markov Random Fields with symmetric positional information, resulting in improved performance as shown in empirical tests and a user study.
Recent procedural content generation via machine learning (PCGML) methods allow learning from existing content to produce similar content automatically. While these approaches are able to generate content for different games (e.g. Super Mario Bros., DOOM, Zelda, and Kid Icarus), it is an open questions how well these approaches can capture large-scale visual patterns such as symmetry. In this paper, we propose match-three games as a domain to test PCGML algorithms regarding their ability to generate suitable patterns. We demonstrate that popular algorithm such as Generative Adversarial Networks struggle in this domain and propose adaptations to improve their performance. In particular we augment the neighborhood of a Markov Random Fields approach to not only take local but also symmetric positional information into account. We conduct several empirical tests including a user study that show the improvements achieved by the proposed modifications, and obtain promising results.