mlsanityData to 7 Oct 2026

Scaling MAP-Elites to Deep Neuroevolution

arXiv 2003.01825 ↗First posted 3 Mar 2020cs.NE cs.AI cs.LGcited by 38

Not on the map. Why?

Abstract (arXiv)

Quality-Diversity (QD) algorithms, and MAP-Elites (ME) in particular, have proven very useful for a broad range of applications including enabling real robots to recover quickly from joint damage, solving strongly deceptive maze tasks or evolving robot morphologies to discover new gaits. However, present implementations of MAP-Elites and other QD algorithms seem to be limited to low-dimensional controllers with far fewer parameters than modern deep neural network models. In this paper, we propose to leverage the efficiency of Evolution Strategies (ES) to scale MAP-Elites to high-dimensional controllers parameterized by large neural networks. We design and evaluate a new hybrid algorithm called MAP-Elites with Evolution Strategies (ME-ES) for post-damage recovery in a difficult high-dimensional control task where traditional ME fails. Additionally, we show that ME-ES performs efficient exploration, on par with state-of-the-art exploration algorithms in high-dimensional control tasks with strongly deceptive rewards.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 14; 2023: 14; 2024: 3; 2025: 2.

38 papers.

Sort:

By area:

  1. 2021Differentiable Quality Diversitycited by 71
  2. 2022Deep Surrogate Assisted Generation of Environmentscited by 40
  3. 2022Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learningcited by 37
  4. 2021Illuminating Diverse Neural Cellular Automata for Level Generationcited by 35
  5. 2023pyribs: A Bare-Bones Python Library for Quality Diversity Optimizationcited by 29
  6. 2022Covariance Matrix Adaptation MAP-Annealingcited by 24
  7. 2023Evolutionary Reinforcement Learning: A Surveycited by 24
  8. 2022Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discoverycited by 23
  9. 2021Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolutioncited by 20
  10. 2021Dynamics-Aware Quality-Diversity for Efficient Learning of Skill Repertoirescited by 20
  11. 2023Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learningcited by 20
  12. 2022Multi-Objective Quality Diversity Optimizationcited by 18
26 more
  1. 2023QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Accelerationcited by 16
  2. 2022Accelerated Quality-Diversity through Massive Parallelismcited by 14
  3. 2024Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Criticscited by 13
  4. 2022Training Diverse High-Dimensional Controllers by Scaling Covariance Matrix Adaptation MAP-Annealingcited by 10
  5. 2022Benchmarking Quality-Diversity Algorithms on Neuroevolution for Reinforcement Learningcited by 10
  6. 2023The Quality-Diversity Transformer: Generating Behavior-Conditioned Trajectories with Decision Transformerscited by 10
  7. 2021Few-shot Quality-Diversity Optimizationcited by 8
  8. 2022Learning to Walk Autonomously via Reset-Free Quality-Diversitycited by 7
  9. 2022Quality Diversity Evolutionary Learning of Decision Treescited by 7
  10. 2024Large Language Models as In-context AI Generators for Quality-Diversitycited by 7
  11. 2023Synergizing Quality-Diversity with Descriptor-Conditioned Reinforcement Learningcited by 6
  12. 2022Fast Population-Based Reinforcement Learning on a Single Machinecited by 5
  13. 2023Understanding the Synergies between Quality-Diversity and Deep Reinforcement Learningcited by 5
  14. 2023Evolving Populations of Diverse RL Agents with MAP-Elitescited by 5
  15. 2023Diversity from Human Feedbackcited by 5
  16. 2022Assessing Quality-Diversity Neuro-Evolution Algorithms Performance in Hard Exploration Problemscited by 4
  17. 2023Mix-ME: Quality-Diversity for Multi-Agent Learningcited by 4
  18. 2023Don't Bet on Luck Alone: Enhancing Behavioral Reproducibility of Quality-Diversity Solutions in Uncertain Domainscited by 3
  19. 2023Efficient Quality-Diversity Optimization through Diverse Quality Speciescited by 3
  20. 2023Enhancing MAP-Elites with Multiple Parallel Evolution Strategiescited by 2
  21. 2022Towards QD-suite: developing a set of benchmarks for Quality-Diversity algorithmscited by 1
  22. 2023Latent-Conditioned Policy Gradient for Multi-Objective Deep Reinforcement Learningcited by 1
  23. 2024Quality-Diversity with Limited Resourcescited by 1
  24. 2025Expedition & Expansion: Leveraging Semantic Representations for Goal-Directed Exploration in Continuous Cellular Automatacited by 1
  25. 2022Efficient Exploration using Model-Based Quality-Diversity with Gradientscited by 0
  26. 2025Scaling Policy Gradient Quality-Diversity with Massive Parallelization via Behavioral Variationscited by 0