Interactive evolution and exploration within latent level-design space of generative adversarial networks

Schrum，Jacob1; Gutierrez，Jake1; Volz，Vanessa2; Liu，Jialin3; Lucas，Simon4; Risi，Sebastian5

10.1145/3377930.3389821

2020-06-25

GECCO 2020 - Proceedings of the 2020 Genetic and Evolutionary Computation Conference

148-156

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.

Generative adversarial network Interactive evolution Latent variable evolution Procedural content generation Video games

其他

英语

EI

20204009295505

Human computer interaction ; Space research ; Interactive computer graphics

Space Research:656.2 ; Artificial Intelligence:723.4 ; Computer Applications:723.5

2-s2.0-85091745122

Scopus

1.Southwestern University,Georgetown,United States
2.Modl.ai,Copenhagen,Denmark
3.Southern University of Science and Technology,Shenzhen,China
4.Queen Mary University of London,London,United Kingdom
5.IT University of Copenhagen,Copenhagen,Denmark

Schrum，Jacob,Gutierrez，Jake,Volz，Vanessa,et al. Interactive evolution and exploration within latent level-design space of generative adversarial networks[C],2020:148-156.