# Evolving Populations of Diverse RL Agents with MAP-Elites

arXiv: https://arxiv.org/abs/2303.12803 · HTML: https://mlsanity.com/paper/2303.12803/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 41 references that are in the map.
- First posted on arXiv 9 Mar 2023.

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

- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation](https://mlsanity.com/paper/2106.13281/) (2021)
- [Population Based Training of Neural Networks](https://mlsanity.com/paper/1711.09846/) (2017)
- [Robots that can adapt like animals](https://mlsanity.com/paper/1407.3501/) (2014)
- [Effective Diversity in Population Based Reinforcement Learning](https://mlsanity.com/paper/2002.00632/) (2020)
- [Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents](https://mlsanity.com/paper/1712.06560/) (2017)
- [Evolution-Guided Policy Gradient in Reinforcement Learning](https://mlsanity.com/paper/1805.07917/) (2018)
- [The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities](https://mlsanity.com/paper/1803.03453/) (2018)
- [Covariance Matrix Adaptation for the Rapid Illumination of Behavior Space](https://mlsanity.com/paper/1912.02400/) (2019)
- [Differentiable Quality Diversity](https://mlsanity.com/paper/2106.03894/) (2021)
- [Using Centroidal Voronoi Tessellations to Scale Up the Multi-dimensional Archive of Phenotypic Elites Algorithm](https://mlsanity.com/paper/1610.05729/) (2016)
- [On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning](https://mlsanity.com/paper/2102.13651/) (2021)
- [CEM-RL: Combining evolutionary and gradient-based methods for policy search](https://mlsanity.com/paper/1810.01222/) (2018)
- [Diversity Policy Gradient for Sample Efficient Quality-Diversity Optimization](https://mlsanity.com/paper/2006.08505/) (2020)
- [Procedural Content Generation through Quality Diversity](https://mlsanity.com/paper/1907.04053/) (2019)
- [Discovering the Elite Hypervolume by Leveraging Interspecies Correlation](https://mlsanity.com/paper/1804.03906/) (2018)
- [GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms](https://mlsanity.com/paper/1802.05054/) (2018)
- [Data-Efficient Design Exploration through Surrogate-Assisted Illumination](https://mlsanity.com/paper/1806.05865/) (2018)
- [Scaling MAP-Elites to Deep Neuroevolution](https://mlsanity.com/paper/2003.01825/) (2020)
- [Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learning](https://mlsanity.com/paper/2202.03666/) (2022)
- [Collaborative Evolutionary Reinforcement Learning](https://mlsanity.com/paper/1905.00976/) (2019)
- [EvoJAX: Hardware-Accelerated Neuroevolution](https://mlsanity.com/paper/2202.05008/) (2022)
- [Generating and Blending Game Levels via Quality-Diversity in the Latent Space of a Variational Autoencoder](https://mlsanity.com/paper/2102.12463/) (2021)
- [Population-Guided Parallel Policy Search for Reinforcement Learning](https://mlsanity.com/paper/2001.02907/) (2020)
- [Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolution](https://mlsanity.com/paper/2104.13424/) (2021)
- [Hierarchical Behavioral Repertoires with Unsupervised Descriptors](https://mlsanity.com/paper/1804.07127/) (2018)
- [Fast Population-Based Reinforcement Learning on a Single Machine](https://mlsanity.com/paper/2206.08888/) (2022)

## Built on by (most cited first, 5 of 5)

- [PolyNet: Learning Diverse Solution Strategies for Neural Combinatorial Optimization](https://mlsanity.com/paper/2402.14048/) (2024)
- [Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning](https://mlsanity.com/paper/2305.13795/) (2023)
- [QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Acceleration](https://mlsanity.com/paper/2308.03665/) (2023)
- [Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models](https://mlsanity.com/paper/2506.07121/) (2025)
- [Synergizing Quality-Diversity with Descriptor-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2401.08632/) (2023)

## Abstract (arXiv)

Quality Diversity (QD) has emerged as a powerful alternative optimization paradigm that aims at generating large and diverse collections of solutions, notably with its flagship algorithm MAP-ELITES (ME) which evolves solutions through mutations and crossovers. While very effective for some unstructured problems, early ME implementations relied exclusively on random search to evolve the population of solutions, rendering them notoriously sample-inefficient for high-dimensional problems, such as when evolving neural networks. Follow-up works considered exploiting gradient information to guide the search in order to address these shortcomings through techniques borrowed from either Black-Box Optimization (BBO) or Reinforcement Learning (RL). While mixing RL techniques with ME unlocked state-of-the-art performance for robotics control problems that require a good amount of exploration, it also plagued these ME variants with limitations common among RL algorithms that ME was free of, such as hyperparameter sensitivity, high stochasticity as well as training instability, including when the population size increases as some components are shared across the population in recent approaches. Furthermore, existing approaches mixing ME with RL tend to be tied to a specific RL algorithm, which effectively prevents their use on problems where the corresponding RL algorithm fails. To address these shortcomings, we introduce a flexible framework that allows the use of any RL algorithm and alleviates the aforementioned limitations by evolving populations of agents (whose definition include hyperparameters and all learnable parameters) instead of just policies. We demonstrate the benefits brought about by our framework through extensive numerical experiments on a number of robotics control problems, some of which with deceptive rewards, taken from the QD-RL literature.