DOOM Level Generation using Generative Adversarial Networks

TL;DR

This paper explores using GANs to generate DOOM levels by learning from human-designed content, analyzing topological features, and comparing different training approaches.

Contribution

It introduces a method combining topological features with GANs to improve DOOM level generation quality.

Findings

GANs can capture the intrinsic structure of DOOM levels.

Including topological features improves level similarity to human designs.

Generated levels show promise for first-person shooter game development.

Abstract

We applied Generative Adversarial Networks (GANs) to learn a model of DOOM levels from human-designed content. Initially, we analysed the levels and extracted several topological features. Then, for each level, we extracted a set of images identifying the occupied area, the height map, the walls, and the position of game objects. We trained two GANs: one using plain level images, one using both the images and some of the features extracted during the preliminary analysis. We used the two networks to generate new levels and compared the results to assess whether the network trained using also the topological features could generate levels more similar to human-designed ones. Our results show that GANs can capture intrinsic structure of DOOM levels and appears to be a promising approach to level generation in first person shooter games.