Generating and Blending Game Levels via Quality-Diversity in the Latent Space of a Variational Autoencoder

TL;DR

This paper introduces a novel method combining variational autoencoders and quality-diversity algorithms to generate and blend diverse, playable game levels across multiple platformer games by exploring their shared latent space.

Contribution

It presents a new approach that integrates VAEs with MAP-Elites to generate and blend game levels, enabling diversity and playability in both individual and combined game domains.

Findings

Generated diverse, playable levels for five individual games.

Successfully blended levels across three games in the domain.

The approach illuminates game-specific regions in the latent space.

Abstract

Several works have demonstrated the use of variational autoencoders (VAEs) for generating levels in the style of existing games and blending levels across different games. Further, quality-diversity (QD) algorithms have also become popular for generating varied game content by using evolution to explore a search space while focusing on both variety and quality. To reap the benefits of both these approaches, we present a level generation and game blending approach that combines the use of VAEs and QD algorithms. Specifically, we train VAEs on game levels and run the MAP-Elites QD algorithm using the learned latent space of the VAE as the search space. The latent space captures the properties of the games whose levels we want to generate and blend, while MAP-Elites searches this latent space to find a diverse set of levels optimizing a given objective such as playability. We test our method using models for 5 different platformer games as well as a blended domain spanning 3 of these games. We refer to using MAP-Elites for blending as Blend-Elites. Our results show that MAP-Elites in conjunction with VAEs enables the generation of a diverse set of playable levels not just for each individual game but also for the blended domain while illuminating game-specific regions of the blended latent space.