Procedural content generation of puzzle games using conditional generative adversarial networks

TL;DR

This paper explores using conditional GANs to generate puzzle game levels, focusing on controlling map shape and piece distribution, with promising results for shape but challenges in piece distribution.

Contribution

It introduces a parameterized conditional GAN approach for puzzle level generation and analyzes its effectiveness in controlling specific level features.

Findings

GANs effectively approximate map shape conditions

Difficulty in accurately modeling piece distribution

Potential for architecture improvements to enhance results

Abstract

In this article, we present an experimental approach to using parameterized Generative Adversarial Networks (GANs) to produce levels for the puzzle game Lily's Garden. We extract two condition vectors from the real levels in an effort to control the details of the GAN's outputs. While the GANs perform well in approximating the first condition (map shape), they struggle to approximate the second condition (piece distribution). We hypothesize that this might be improved by trying out alternative architectures for both the Generator and Discriminator of the GANs.