# Illuminating Mario Scenes in the Latent Space of a Generative Adversarial Network

arXiv: https://arxiv.org/abs/2007.05674 · HTML: https://mlsanity.com/paper/2007.05674/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jul 2020.

## Built on by (most cited first, 30 of 52)

- [Differentiable Quality Diversity](https://mlsanity.com/paper/2106.03894/) (2021)
- [MarioGPT: Open-Ended Text2Level Generation through Large Language Models](https://mlsanity.com/paper/2302.05981/) (2023)
- [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)
- [Illuminating Diverse Neural Cellular Automata for Level Generation](https://mlsanity.com/paper/2109.05489/) (2021)
- [Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models](https://mlsanity.com/paper/2412.02980/) (2024)
- [pyribs: A Bare-Bones Python Library for Quality Diversity Optimization](https://mlsanity.com/paper/2303.00191/) (2023)
- [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)
- [Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning](https://mlsanity.com/paper/2305.13795/) (2023)
- [Multi-Robot Coordination and Layout Design for Automated Warehousing](https://mlsanity.com/paper/2305.06436/) (2023)
- [Illuminating the Space of Beatable Lode Runner Levels Produced By Various Generative Adversarial Networks](https://mlsanity.com/paper/2101.07868/) (2021)
- [Accelerated Quality-Diversity through Massive Parallelism](https://mlsanity.com/paper/2202.01258/) (2022)
- [Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution](https://mlsanity.com/paper/2208.04957/) (2022)
- [Benchmarking Quality-Diversity Algorithms on Neuroevolution for Reinforcement Learning](https://mlsanity.com/paper/2211.02193/) (2022)
- [Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization](https://mlsanity.com/paper/2310.12103/) (2023)
- [Arbitrarily Scalable Environment Generators via Neural Cellular Automata](https://mlsanity.com/paper/2310.18622/) (2023)
- [Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models](https://mlsanity.com/paper/2506.07121/) (2025)
- [Surrogate Assisted Generation of Human-Robot Interaction Scenarios](https://mlsanity.com/paper/2304.13787/) (2023)
- [Learning to Walk Autonomously via Reset-Free Quality-Diversity](https://mlsanity.com/paper/2204.03655/) (2022)
- [Diversity from Human Feedback](https://mlsanity.com/paper/2310.06648/) (2023)
- [Measuring Diversity of Game Scenarios](https://mlsanity.com/paper/2404.15192/) (2024)
- [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)
- [Quality-Diversity Generative Sampling for Learning with Synthetic Data](https://mlsanity.com/paper/2312.14369/) (2023)
- [Using Multiple Generative Adversarial Networks to Build Better-Connected Levels for Mega Man](https://mlsanity.com/paper/2102.00337/) (2021)
- [Fast Game Content Adaptation Through Bayesian-based Player Modelling](https://mlsanity.com/paper/2105.08484/) (2021)
- [Tackling Neural Architecture Search With Quality Diversity Optimization](https://mlsanity.com/paper/2208.00204/) (2022)
- [Don't Bet on Luck Alone: Enhancing Behavioral Reproducibility of Quality-Diversity Solutions in Uncertain Domains](https://mlsanity.com/paper/2304.03672/) (2023)
- [AutoQD: Automatic Discovery of Diverse Behaviors with Quality-Diversity Optimization](https://mlsanity.com/paper/2506.05634/) (2025)

## Abstract (arXiv)

Generative adversarial networks (GANs) are quickly becoming a ubiquitous approach to procedurally generating video game levels. While GAN generated levels are stylistically similar to human-authored examples, human designers often want to explore the generative design space of GANs to extract interesting levels. However, human designers find latent vectors opaque and would rather explore along dimensions the designer specifies, such as number of enemies or obstacles. We propose using state-of-the-art quality diversity algorithms designed to optimize continuous spaces, i.e. MAP-Elites with a directional variation operator and Covariance Matrix Adaptation MAP-Elites, to efficiently explore the latent space of a GAN to extract levels that vary across a set of specified gameplay measures. In the benchmark domain of Super Mario Bros, we demonstrate how designers may specify gameplay measures to our system and extract high-quality (playable) levels with a diverse range of level mechanics, while still maintaining stylistic similarity to human authored examples. An online user study shows how the different mechanics of the automatically generated levels affect subjective ratings of their perceived difficulty and appearance.