Controllable Level Blending between Games using Variational Autoencoders

TL;DR

This paper presents a VAE-based method for blending and evolving game levels from Super Mario Bros. and Kid Icarus, enabling controllable, property-specific level generation for co-creative design.

Contribution

It introduces a novel VAE approach for level blending and evolution, improving upon prior blending techniques with controllability and property constraints.

Findings

VAE effectively captures combined level features from both games.

Evolutionary search in latent space produces levels with desired properties.

VAE-based method outperforms GAN and VAE-GAN in level blending tasks.

Abstract

Previous work explored blending levels from existing games to create levels for a new game that mixes properties of the original games. In this paper, we use Variational Autoencoders (VAEs) for improving upon such techniques. VAEs are artificial neural networks that learn and use latent representations of datasets to generate novel outputs. We train a VAE on level data from Super Mario Bros. and Kid Icarus, enabling it to capture the latent space spanning both games. We then use this space to generate level segments that combine properties of levels from both games. Moreover, by applying evolutionary search in the latent space, we evolve level segments satisfying specific constraints. We argue that these affordances make the VAE-based approach especially suitable for co-creative level design and compare its performance with similar generative models like the GAN and the VAE-GAN.