# CPPN2GAN: Combining Compositional Pattern Producing Networks and GANs for Large-scale Pattern Generation

arXiv: https://arxiv.org/abs/2004.01703 · HTML: https://mlsanity.com/paper/2004.01703/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2020.

## Built on by (most cited first, 19 of 19)

- [Open-Ended Learning Leads to Generally Capable Agents](https://mlsanity.com/paper/2107.12808/) (2021)
- [Differentiable Quality Diversity](https://mlsanity.com/paper/2106.03894/) (2021)
- [Deep Surrogate Assisted Generation of Environments](https://mlsanity.com/paper/2206.04199/) (2022)
- [On the Importance of Environments in Human-Robot Coordination](https://mlsanity.com/paper/2106.10853/) (2021)
- [Generating and Blending Game Levels via Quality-Diversity in the Latent Space of a Variational Autoencoder](https://mlsanity.com/paper/2102.12463/) (2021)
- [Covariance Matrix Adaptation MAP-Annealing](https://mlsanity.com/paper/2205.10752/) (2022)
- [Procedural Content Generation in Games: A Survey with Insights on Emerging LLM Integration](https://mlsanity.com/paper/2410.15644/) (2024)
- [Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning](https://mlsanity.com/paper/2305.13795/) (2023)
- [Illuminating the Space of Beatable Lode Runner Levels Produced By Various Generative Adversarial Networks](https://mlsanity.com/paper/2101.07868/) (2021)
- [Surrogate Assisted Generation of Human-Robot Interaction Scenarios](https://mlsanity.com/paper/2304.13787/) (2023)
- [Mario Plays on a Manifold: Generating Functional Content in Latent Space through Differential Geometry](https://mlsanity.com/paper/2206.00106/) (2022)
- [Hybrid Encoding For Generating Large Scale Game Level Patterns With Local Variations](https://mlsanity.com/paper/2105.12960/) (2021)
- [Evolving Flying Machines in Minecraft Using Quality Diversity](https://mlsanity.com/paper/2302.00782/) (2023)
- [Gradient-Informed Quality Diversity for the Illumination of Discrete Spaces](https://mlsanity.com/paper/2306.05138/) (2023)
- [Using Multiple Generative Adversarial Networks to Build Better-Connected Levels for Mega Man](https://mlsanity.com/paper/2102.00337/) (2021)
- [Augmentative Topology Agents For Open-Ended Learning](https://mlsanity.com/paper/2210.11442/) (2022)
- [Discount Model Search for Quality Diversity Optimization in High-Dimensional Measure Spaces](https://mlsanity.com/paper/2601.01082/) (2026)
- [Combining Evolutionary Search with Behaviour Cloning for Procedurally Generated Content](https://mlsanity.com/paper/2207.14772/) (2022)
- [Text-to-Level Diffusion Models With Various Text Encoders for Super Mario Bros](https://mlsanity.com/paper/2507.00184/) (2025)

## Abstract (arXiv)

Generative Adversarial Networks (GANs) are proving to be a powerful indirect genotype-to-phenotype mapping for evolutionary search, but they have limitations. In particular, GAN output does not scale to arbitrary dimensions, and there is no obvious way of combining multiple GAN outputs into a cohesive whole, which would be useful in many areas, such as the generation of video game levels. Game levels often consist of several segments, sometimes repeated directly or with variation, organized into an engaging pattern. Such patterns can be produced with Compositional Pattern Producing Networks (CPPNs). Specifically, a CPPN can define latent vector GAN inputs as a function of geometry, which provides a way to organize level segments output by a GAN into a complete level. This new CPPN2GAN approach is validated in both Super Mario Bros. and The Legend of Zelda. Specifically, divergent search via MAP-Elites demonstrates that CPPN2GAN can better cover the space of possible levels. The layouts of the resulting levels are also more cohesive and aesthetically consistent.