Sequential Segment-based Level Generation and Blending using Variational Autoencoders

TL;DR

This paper introduces a sequential VAE-based method for generating coherent, arbitrarily long game levels that can blend levels from different games by learning logical segment progression and placement.

Contribution

It presents a novel sequential VAE model combined with a classifier for logical segment placement, enabling coherent and cross-game level blending.

Findings

Produces more coherent levels than previous methods.

Capable of blending levels across different games.

Generates arbitrarily long levels with logical segment progression.

Abstract

Existing methods of level generation using latent variable models such as VAEs and GANs do so in segments and produce the final level by stitching these separately generated segments together. In this paper, we build on these methods by training VAEs to learn a sequential model of segment generation such that generated segments logically follow from prior segments. By further combining the VAE with a classifier that determines whether to place the generated segment to the top, bottom, left or right of the previous segment, we obtain a pipeline that enables the generation of arbitrarily long levels that progress in any of these four directions and are composed of segments that logically follow one another. In addition to generating more coherent levels of non-fixed length, this method also enables implicit blending of levels from separate games that do not have similar orientation. We demonstrate our approach using levels from Super Mario Bros., Kid Icarus and Mega Man, showing that our method produces levels that are more coherent than previous latent variable-based approaches and are capable of blending levels across games.