English

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

Neural and Evolutionary Computing 2020-04-02 v1 Artificial Intelligence

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.

Keywords

Cite

@article{arxiv.2004.00151,
  title  = {Interactive Evolution and Exploration Within Latent Level-Design Space of Generative Adversarial Networks},
  author = {Jacob Schrum and Jake Gutierrez and Vanessa Volz and Jialin Liu and Simon Lucas and Sebastian Risi},
  journal= {arXiv preprint arXiv:2004.00151},
  year   = {2020}
}

Comments

GECCO 2020

R2 v1 2026-06-23T14:34:38.757Z