Capturing Local and Global Patterns in Procedural Content Generation via Machine Learning

TL;DR

This paper evaluates how well machine learning methods can generate large-scale visual patterns in procedural content, focusing on match-three games, and proposes modifications to improve pattern symmetry capture.

Contribution

It introduces adaptations to existing algorithms, including Markov Random Fields, to better capture symmetry and large-scale patterns in game content generation.

Findings

Markov Random Fields with symmetry considerations outperform standard methods

GANs struggle with large-scale pattern generation in this domain

User studies confirm the effectiveness of proposed modifications

Abstract

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.