Procedural content generation of puzzle games using conditional generative adversarial networks
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 10 of its 20 references that are in the map. First posted on arXiv 26 Jun 2023.
Builds on
10 of 20 references.
References · 10
- 2016Improved Techniques for Training GANscited by 2,938
- 2017Improved Training of Wasserstein GANscited by 2,223
- 2014Conditional Generative Adversarial Netscited by 2,152
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
- 2016NIPS 2016 Tutorial: Generative Adversarial Networkscited by 284
- 2017Procedural Content Generation via Machine Learning (PCGML)cited by 136
- 2018Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Networkcited by 76
- 2019Bootstrapping Conditional GANs for Video Game Level Generationcited by 35
- 2018DOOM Level Generation using Generative Adversarial Networkscited by 15
- 2020Controllable Level Blending between Games using Variational Autoencoderscited by 14
Built on by
Citing papers per year: 2024: 3.
3 papers.