# Vector Quantized-Elites: Unsupervised and Problem-Agnostic Quality-Diversity Optimization

arXiv: https://arxiv.org/abs/2504.08057 · HTML: https://mlsanity.com/paper/2504.08057/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 53 references that are in the map.
- First posted on arXiv 10 Apr 2025.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://mlsanity.com/paper/2209.00796/) (2022)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [Diversity is All You Need: Learning Skills without a Reward Function](https://mlsanity.com/paper/1802.06070/) (2018)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [Variational Intrinsic Control](https://mlsanity.com/paper/1611.07507/) (2016)
- [Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts](https://mlsanity.com/paper/2402.16822/) (2024)
- [Robots that can adapt like animals](https://mlsanity.com/paper/1407.3501/) (2014)
- [Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills](https://mlsanity.com/paper/2002.03647/) (2020)
- [Quality and Diversity Optimization: A Unifying Modular Framework](https://mlsanity.com/paper/1708.09251/) (2017)
- [Using Centroidal Voronoi Tessellations to Scale Up the Multi-dimensional Archive of Phenotypic Elites Algorithm](https://mlsanity.com/paper/1610.05729/) (2016)
- [Predicting Video with VQVAE](https://mlsanity.com/paper/2103.01950/) (2021)
- [Quality-Diversity Optimization: a novel branch of stochastic optimization](https://mlsanity.com/paper/2012.04322/) (2020)
- [Autonomous skill discovery with Quality-Diversity and Unsupervised Descriptors](https://mlsanity.com/paper/1905.11874/) (2019)
- [Robust Training of Vector Quantized Bottleneck Models](https://mlsanity.com/paper/2005.08520/) (2020)
- [Unsupervised Behaviour Discovery with Quality-Diversity Optimisation](https://mlsanity.com/paper/2106.05648/) (2021)
- [Reset-free Trial-and-Error Learning for Robot Damage Recovery](https://mlsanity.com/paper/1610.04213/) (2016)
- [GAVEL: Generating Games Via Evolution and Language Models](https://mlsanity.com/paper/2407.09388/) (2024)
- [Unsupervised Learning and Exploration of Reachable Outcome Space](https://mlsanity.com/paper/1909.05508/) (2019)
- [Hierarchical Behavioral Repertoires with Unsupervised Descriptors](https://mlsanity.com/paper/1804.07127/) (2018)
- [Learning Disentangled Phone and Speaker Representations in a Semi-Supervised VQ-VAE Paradigm](https://mlsanity.com/paper/2010.10727/) (2020)
- [A Comparison of Discrete Latent Variable Models for Speech Representation Learning](https://mlsanity.com/paper/2010.14230/) (2020)
- [Discovering and Exploiting Sparse Rewards in a Learned Behavior Space](https://mlsanity.com/paper/2111.01919/) (2021)
- [Topic-VQ-VAE: Leveraging Latent Codebooks for Flexible Topic-Guided Document Generation](https://mlsanity.com/paper/2312.11532/) (2023)
- [Performance and Interpretability Comparisons of Supervised Machine Learning Algorithms: An Empirical Study](https://mlsanity.com/paper/2204.12868/) (2022)
- [Quality-Diversity Meta-Evolution: customising behaviour spaces to a meta-objective](https://mlsanity.com/paper/2109.03918/) (2021)

## Built on by (most cited first, 1 of 1)

- [Learning Reusable Hybrid Motion Priors for Humanoid Locomotion from Motion Imitation](https://mlsanity.com/paper/2607.24083/) (2026)

## Abstract (arXiv)

Quality-Diversity algorithms have transformed optimization by prioritizing the discovery of diverse, high-performing solutions over a single optimal result. However, traditional Quality-Diversity methods, such as MAP-Elites, rely heavily on predefined behavior descriptors and complete prior knowledge of the task to define the behavior space grid, limiting their flexibility and applicability. In this work, we introduce Vector Quantized-Elites (VQ-Elites), a novel Quality-Diversity algorithm that autonomously constructs a structured behavior space grid using unsupervised learning, eliminating the need for prior task-specific knowledge. At the core of VQ-Elites is the integration of Vector Quantized Variational Autoencoders, which enables the dynamic learning of behavior descriptors and the generation of a structured, rather than unstructured, behavior space grid -- a significant advancement over existing unsupervised Quality-Diversity approaches. This design establishes VQ-Elites as a flexible, robust, and task-agnostic optimization framework. To further enhance the performance of unsupervised Quality-Diversity algorithms, we introduce behavior space bounding and cooperation mechanisms, which significantly improve convergence and performance, as well as the Effective Diversity Ratio and Coverage Diversity Score, two novel metrics that quantify the actual diversity in the unsupervised setting. We validate VQ-Elites on robotic arm pose-reaching, mobile robot space-covering, and MiniGrid exploration tasks. The results demonstrate its ability to efficiently generate diverse, high-quality solutions, emphasizing its adaptability, scalability, robustness to hyperparameters, and potential to extend Quality-Diversity optimization to complex, previously inaccessible domains.