Illuminating Mario Scenes in the Latent Space of a Generative Adversarial Network
This addresses the need for human designers to efficiently explore generative design spaces in video game level creation, though it is incremental as it applies existing algorithms to a specific domain.
The paper tackled the problem of exploring the latent space of a GAN for generating video game levels by allowing designers to specify gameplay measures like enemy count, using quality diversity algorithms to extract diverse, playable levels. The result demonstrated high-quality levels with varied mechanics and stylistic similarity to human examples, supported by a user study on perceived difficulty and appearance.
Generative adversarial networks (GANs) are quickly becoming a ubiquitous approach to procedurally generating video game levels. While GAN generated levels are stylistically similar to human-authored examples, human designers often want to explore the generative design space of GANs to extract interesting levels. However, human designers find latent vectors opaque and would rather explore along dimensions the designer specifies, such as number of enemies or obstacles. We propose using state-of-the-art quality diversity algorithms designed to optimize continuous spaces, i.e. MAP-Elites with a directional variation operator and Covariance Matrix Adaptation MAP-Elites, to efficiently explore the latent space of a GAN to extract levels that vary across a set of specified gameplay measures. In the benchmark domain of Super Mario Bros, we demonstrate how designers may specify gameplay measures to our system and extract high-quality (playable) levels with a diverse range of level mechanics, while still maintaining stylistic similarity to human authored examples. An online user study shows how the different mechanics of the automatically generated levels affect subjective ratings of their perceived difficulty and appearance.