CPPN2GAN: Combining Compositional Pattern Producing Networks and GANs for Large-scale Pattern Generation

Item

Title
CPPN2GAN: Combining Compositional Pattern Producing Networks and GANs for Large-scale Pattern Generation
Creator
Schrum, Jacob
Volz, Vanessa
Risi, Sebastian
Date
2020
Language
English
Publisher
Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2020)
Identifier
Jacob Schrum, Vanessa Volz, and Sebastian Risi. 2020. CPPN2GAN: combining compositional pattern producing networks and GANs for large-scale pattern generation. In Proceedings of the 2020 Genetic and Evolutionary Computation Conference (GECCO '20). Association for Computing Machinery, New York, NY, USA, 139–147. DOI:https://doi.org/10.1145/3377930.3389822
Subject
Computing methodologies
Machine learning
Machine learning approaches
Bio-inspired approaches
Generative and developmental approaches
Abstract
Generative Adversarial Networks (GANs) are proving to be a powerful indirect genotype-to-phenotype mapping for evolutionary search, but they have limitations. In particular, GAN output does not scale to arbitrary dimensions, and there is no obvious way of combining multiple GAN outputs into a cohesive whole, which would be useful in many areas, such as the generation of video game levels. Game levels often consist of several segments, sometimes repeated directly or with variation, organized into an engaging pattern. Such patterns can be produced with Compositional Pattern Producing Networks (CPPNs). Specifically, a CPPN can define latent vector GAN inputs as a function of geometry, which provides a way to organize level segments output by a GAN into a complete level. This new CPPN2GAN approach is validated in both Super Mario Bros. and The Legend of Zelda. Specifically, divergent search via MAP-Elites demonstrates that CPPN2GAN can better cover the space of possible levels. The layouts of the resulting levels are also more cohesive and aesthetically consistent.