Interactive Evolution and Exploration Within Latent Level-Design Space of Generative Adversarial Networks

Item

Title
Interactive Evolution and Exploration Within Latent Level-Design Space of Generative Adversarial Networks
Creator
Schrum, Jacob
Gutierrez, Jake
Volz, Vanessa
Liu, Jialin
Lucas, Simon M.
Risi, Sebastian
Date
2020
Language
English
Publisher
Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2020)
Identifier
Jacob Schrum, Jake Gutierrez, Vanessa Volz, Jialin Liu, Simon Lucas, and Sebastian Risi. 2020. Interactive evolution and exploration within latent level-design space of generative adversarial networks. In Proceedings of the 2020 Genetic and Evolutionary Computation Conference (GECCO '20). Association for Computing Machinery, New York, NY, USA, 148–156. DOI:https://doi.org/10.1145/3377930.3389821
Subject
Computing methodologies
Machine learning
Machine learning approaches
Bio-inspired approaches
Genetic algorithms
Learning latent representations
Neural networks

Abstract
Generative Adversarial Networks (GANs) are an emerging form of indirect encoding. The GAN is trained to induce a latent space on training data, and a real-valued evolutionary algorithm can search that latent space. Such Latent Variable Evolution (LVE) has recently been applied to game levels. However, it is hard for objective scores to capture level features that are appealing to players. Therefore, this paper introduces a tool for interactive LVE of tile-based levels for games. The tool also allows for direct exploration of the latent dimensions, and allows users to play discovered levels. The tool works for a variety of GAN models trained for both Super Mario Bros. and The Legend of Zelda, and is easily generalizable to other games. A user study shows that both the evolution and latent space exploration features are appreciated, with a slight preference for direct exploration, but combining these features allows users to discover even better levels. User feedback also indicates how this system could eventually grow into a commercial design tool, with the addition of a few enhancements.