Latent Combinational Game Design

TL;DR

This paper introduces a novel deep generative approach using GMVAEs to create blended games from multiple sources, allowing control over the combination proportions and generating playable levels.

Contribution

It proposes a new latent combinational game design method using GMVAEs and hybrid models, enabling controlled blending of different game styles and levels.

Findings

Generated playable blended games with specified proportions

Demonstrated approach on platformers and dungeon games

Compared GMVAE with conditional VAEs showing improved blending

Abstract

We present latent combinational game design -- an approach for generating playable games that blend a given set of games in a desired combination using deep generative latent variable models. We use Gaussian Mixture Variational Autoencoders (GMVAEs) which model the VAE latent space via a mixture of Gaussian components. Through supervised training, each component encodes levels from one game and lets us define blended games as linear combinations of these components. This enables generating new games that blend the input games as well as controlling the relative proportions of each game in the blend. We also extend prior blending work using conditional VAEs and compare against the GMVAE and additionally introduce a hybrid conditional GMVAE (CGMVAE) architecture which lets us generate whole blended levels and layouts. Results show that these approaches can generate playable games that blend the input games in specified combinations. We use both platformers and dungeon-based games to demonstrate our results.