English

Procedural content generation of puzzle games using conditional generative adversarial networks

Artificial Intelligence 2023-06-29 v1 Machine Learning

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.

Keywords

Cite

@article{arxiv.2306.15696,
  title  = {Procedural content generation of puzzle games using conditional generative adversarial networks},
  author = {Andreas Hald and Jens Struckmann Hansen and Jeppe Kristensen and Paolo Burelli},
  journal= {arXiv preprint arXiv:2306.15696},
  year   = {2023}
}

Comments

Proceedings of the 15th International Conference on the Foundations of Digital Games 2020

R2 v1 2026-06-28T11:16:00.479Z