Dungeon and Platformer Level Blending and Generation using Conditional VAEs

TL;DR

This paper introduces a method using conditional variational autoencoders to generate and blend entire levels of platformer and dungeon games, allowing controllable and interconnected level creation across genres.

Contribution

It extends CVAE applications to generate full levels and blend genres, enabling controllable level features and interconnected designs in game level generation.

Findings

Reliable control of door placement in dungeons

Control of progression direction in platformers

Generation of interconnected levels across genres

Abstract

Variational autoencoders (VAEs) have been used in prior works for generating and blending levels from different games. To add controllability to these models, conditional VAEs (CVAEs) were recently shown capable of generating output that can be modified using labels specifying desired content, albeit working with segments of levels and platformers exclusively. We expand these works by using CVAEs for generating whole platformer and dungeon levels, and blending levels across these genres. We show that CVAEs can reliably control door placement in dungeons and progression direction in platformer levels. Thus, by using appropriate labels, our approach can generate whole dungeons and platformer levels of interconnected rooms and segments respectively as well as levels that blend dungeons and platformers. We demonstrate our approach using The Legend of Zelda, Metroid, Mega Man and Lode Runner.