# Procedural Content Generation through Quality Diversity

arXiv: https://arxiv.org/abs/1907.04053 · HTML: https://mlsanity.com/paper/1907.04053/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jul 2019.

## Built on by (most cited first, 30 of 45)

- [Differentiable Quality Diversity](https://mlsanity.com/paper/2106.03894/) (2021)
- [Deep Surrogate Assisted Generation of Environments](https://mlsanity.com/paper/2206.04199/) (2022)
- [Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learning](https://mlsanity.com/paper/2202.03666/) (2022)
- [Generating and Blending Game Levels via Quality-Diversity in the Latent Space of a Variational Autoencoder](https://mlsanity.com/paper/2102.12463/) (2021)
- [Experience-Driven PCG via Reinforcement Learning: A Super Mario Bros Study](https://mlsanity.com/paper/2106.15877/) (2021)
- [Covariance Matrix Adaptation MAP-Annealing](https://mlsanity.com/paper/2205.10752/) (2022)
- [GAVEL: Generating Games Via Evolution and Language Models](https://mlsanity.com/paper/2407.09388/) (2024)
- [Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolution](https://mlsanity.com/paper/2104.13424/) (2021)
- [Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning](https://mlsanity.com/paper/2305.13795/) (2023)
- [DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraft](https://mlsanity.com/paper/2404.15538/) (2024)
- [Accelerated Quality-Diversity through Massive Parallelism](https://mlsanity.com/paper/2202.01258/) (2022)
- [Open-Ended Evolution for Minecraft Building Generation](https://mlsanity.com/paper/2209.03108/) (2022)
- [Few-shot Quality-Diversity Optimization](https://mlsanity.com/paper/2109.06826/) (2021)
- [ChatGPT4PCG Competition: Character-like Level Generation for Science Birds](https://mlsanity.com/paper/2303.15662/) (2023)
- [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)
- [Large Language Models as In-context AI Generators for Quality-Diversity](https://mlsanity.com/paper/2404.15794/) (2024)
- [Understanding the Synergies between Quality-Diversity and Deep Reinforcement Learning](https://mlsanity.com/paper/2303.06164/) (2023)
- [Discovering Generalizable Skills via Automated Generation of Diverse Tasks](https://mlsanity.com/paper/2106.13935/) (2021)
- [Architext: Language-Driven Generative Architecture Design](https://mlsanity.com/paper/2303.07519/) (2023)
- [Evolving Populations of Diverse RL Agents with MAP-Elites](https://mlsanity.com/paper/2303.12803/) (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)
- [Diversity-based Deep Reinforcement Learning Towards Multidimensional Difficulty for Fighting Game AI](https://mlsanity.com/paper/2211.02759/) (2022)
- [Efficient Quality-Diversity Optimization through Diverse Quality Species](https://mlsanity.com/paper/2304.07425/) (2023)
- [Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity](https://mlsanity.com/paper/2411.04466/) (2024)
- [AutoQD: Automatic Discovery of Diverse Behaviors with Quality-Diversity Optimization](https://mlsanity.com/paper/2506.05634/) (2025)
- [Exploring open-ended gameplay features with Micro RollerCoaster Tycoon](https://mlsanity.com/paper/2105.04342/) (2021)
- [Generating Game Levels of Diverse Behaviour Engagement](https://mlsanity.com/paper/2207.02100/) (2022)
- [Illuminating the Space of Dungeon Maps, Locked-door Missions and Enemy Placement Through MAP-Elites](https://mlsanity.com/paper/2202.09301/) (2022)

## Abstract (arXiv)

Quality-diversity (QD) algorithms search for a set of good solutions which cover a space as defined by behavior metrics. This simultaneous focus on quality and diversity with explicit metrics sets QD algorithms apart from standard single- and multi-objective evolutionary algorithms, as well as from diversity preservation approaches such as niching. These properties open up new avenues for artificial intelligence in games, in particular for procedural content generation. Creating multiple systematically varying solutions allows new approaches to creative human-AI interaction as well as adaptivity. In the last few years, a handful of applications of QD to procedural content generation and game playing have been proposed; we discuss these and propose challenges for future work.