CPPN2GAN: Combining Compositional Pattern Producing Networks and GANs for Large-scale Pattern Generation
This addresses the challenge of scalable and organized pattern generation for video game design, representing an incremental improvement over existing methods.
The paper tackles the problem of generating large-scale, cohesive patterns like video game levels by combining Compositional Pattern Producing Networks (CPPNs) and Generative Adversarial Networks (GANs), resulting in improved coverage of level spaces and more cohesive layouts in Super Mario Bros. and The Legend of Zelda.
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.