Controllable Level Blending between Games using Variational Autoencoders
This work addresses the challenge of co-creative level design in game development, offering a controllable method for generating blended levels, though it is incremental as it builds on prior blending techniques with VAEs.
The paper tackled the problem of blending levels from different games to create new levels by using Variational Autoencoders (VAEs) trained on Super Mario Bros. and Kid Icarus data, enabling the generation of level segments that combine properties from both games and evolve to meet specific constraints through evolutionary search.
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.