Interactive Evolution and Exploration Within Latent Level-Design Space of Generative Adversarial Networks
This work addresses the problem of creating engaging game levels for designers and players, but it is incremental as it builds on existing LVE methods by adding interactivity.
The paper tackles the challenge of generating appealing game levels by introducing an interactive tool for Latent Variable Evolution (LVE) that allows users to explore and evolve levels in the latent space of GANs, with a user study showing appreciation for both evolution and exploration features and a slight preference for direct exploration.
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.