TY - GEN
T1 - Interactive Evolution and Exploration within Latent Level-Design Space of Generative Adversarial Networks
AU - Schrum, Jacob
AU - Gutierrez, Jake
AU - Volz, Vanessa
AU - Liu, Jialin
AU - Lucas, Simon
AU - Risi, Sebastian
PY - 2020
Y1 - 2020
N2 - 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.
AB - 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.
KW - procedural content generation
KW - video games
KW - generative adversarial network
KW - interactive evolution
KW - latent variable evolution
U2 - 10.1145/3377930.3389821
DO - 10.1145/3377930.3389821
M3 - Article in proceedings
SN - 9781450371285
SP - 148
EP - 156
BT - Proceedings of the 2020 Genetic and Evolutionary Computation Conference
PB - Association for Computing Machinery
CY - New York, NY, USA
ER -