mlsanityData to 7 Oct 2026

Covariance Matrix Adaptation MAP-Annealing

arXiv 2205.10752 ↗First posted 22 May 2022cs.LG cs.AIcited by 24

Not on the map. Why?

Abstract (arXiv)

Single-objective optimization algorithms search for the single highest-quality solution with respect to an objective. Quality diversity (QD) optimization algorithms, such as Covariance Matrix Adaptation MAP-Elites (CMA-ME), search for a collection of solutions that are both high-quality with respect to an objective and diverse with respect to specified measure functions. However, CMA-ME suffers from three major limitations highlighted by the QD community: prematurely abandoning the objective in favor of exploration, struggling to explore flat objectives, and having poor performance for low-resolution archives. We propose a new quality diversity algorithm, Covariance Matrix Adaptation MAP-Annealing (CMA-MAE), that addresses all three limitations. We provide theoretical justifications for the new algorithm with respect to each limitation. Our theory informs our experiments, which support the theory and show that CMA-MAE achieves state-of-the-art performance and robustness.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 57 of its 91 references that are in the map. First posted on arXiv 22 May 2022.

Builds on

57 of 91 references.

References · 57

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  5. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  6. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  7. 2015Illuminating search spaces by mapping elitescited by 406
  8. 2016The CMA Evolution Strategy: A Tutorialcited by 364
  9. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
  10. 2021Unsolved Problems in ML Safetycited by 291
  11. 2022VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidancecited by 285
  12. 2014Robots that can adapt like animalscited by 203
38 more
  1. 2021CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoderscited by 186
  2. 2016COCO: A Platform for Comparing Continuous Optimizers in a Black-Box Settingcited by 135
  3. 2020Effective Diversity in Population Based Reinforcement Learningcited by 116
  4. 2017Quality and Diversity Optimization: A Unifying Modular Frameworkcited by 111
  5. 2017Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agentscited by 107
  6. 2021Generative Models as a Data Source for Multiview Representation Learningcited by 104
  7. 2018The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communitiescited by 78
  8. 2019Covariance Matrix Adaptation for the Rapid Illumination of Behavior Spacecited by 78
  9. 2021Differentiable Quality Diversitycited by 71
  10. 2016Using Centroidal Voronoi Tessellations to Scale Up the Multi-dimensional Archive of Phenotypic Elites Algorithmcited by 65
  11. 2019This dataset does not exist: training models from generated imagescited by 65
  12. 2020Quality-Diversity Optimization: a novel branch of stochastic optimizationcited by 59
  13. 2019Autonomous skill discovery with Quality-Diversity and Unsupervised Descriptorscited by 57
  14. 2020Diversity Policy Gradient for Sample Efficient Quality-Diversity Optimizationcited by 53
  15. 2020Illuminating Mario Scenes in the Latent Space of a Generative Adversarial Networkcited by 51
  16. 2019Procedural Content Generation through Quality Diversitycited by 45
  17. 2018Discovering the Elite Hypervolume by Leveraging Interspecies Correlationcited by 40
  18. 2018Data-Efficient Design Exploration through Surrogate-Assisted Illuminationcited by 38
  19. 2020Scaling MAP-Elites to Deep Neuroevolutioncited by 38
  20. 2021On the Importance of Environments in Human-Robot Coordinationcited by 37
  21. 2022Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learningcited by 37
  22. 2021Illuminating Diverse Neural Cellular Automata for Level Generationcited by 35
  23. 2019Mapping Hearthstone Deck Spaces through MAP-Elites with Sliding Boundariescited by 32
  24. 2020Imperfect ImaGANation: Implications of GANs Exacerbating Biases on Facial Data Augmentation and Snapchat Selfie Lensescited by 27
  25. 2021Generating and Blending Game Levels via Quality-Diversity in the Latent Space of a Variational Autoencodercited by 27
  26. 2018Talakat: Bullet Hell Generation through Constrained Map-Elitescited by 26
  27. 2021Deep Surrogate Assisted MAP-Elites for Automated Hearthstone Deckbuildingcited by 26
  28. 2020A Quality Diversity Approach to Automatically Generating Human-Robot Interaction Scenarios in Shared Autonomycited by 20
  29. 2021Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolutioncited by 20
  30. 2021Dynamics-Aware Quality-Diversity for Efficient Learning of Skill Repertoirescited by 20
  31. 2020CPPN2GAN: Combining Compositional Pattern Producing Networks and GANs for Large-scale Pattern Generationcited by 19
  32. 2020BOP-Elites, a Bayesian Optimisation algorithm for Quality-Diversity searchcited by 15
  33. 2020Open Questions in Creating Safe Open-ended AI: Tensions Between Control and Creativitycited by 15
  34. 2020Multi-Emitter MAP-Elites: Improving quality, diversity and convergence speed with heterogeneous sets of emitterscited by 14
  35. 2020Model-Based Quality-Diversity Search for Efficient Robot Learningcited by 14
  36. 2021Illuminating the Space of Beatable Lode Runner Levels Produced By Various Generative Adversarial Networkscited by 14
  37. 2022Accelerated Quality-Diversity through Massive Parallelismcited by 14
  38. 2021Sparse Reward Exploration via Novelty Search and Emitterscited by 13

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 7; 2024: 8; 2025: 4; 2026: 4.

24 papers.

Sort:

By area:

  1. 2023pyribs: A Bare-Bones Python Library for Quality Diversity Optimizationcited by 29
  2. 2023Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learningcited by 20
  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. 2024Explainable Benchmarking for Iterative Optimization Heuristicscited by 10
  6. 2023Arbitrarily Scalable Environment Generators via Neural Cellular Automatacited by 9
  7. 2023Surrogate Assisted Generation of Human-Robot Interaction Scenarioscited by 8
  8. 2023Quality Diversity under Sparse Reward and Sparse Interaction: Application to Grasping in Roboticscited by 6
  9. 2023Synergizing Quality-Diversity with Descriptor-Conditioned Reinforcement Learningcited by 6
  10. 2024Parametric-Task MAP-Elitescited by 4
  11. 2024Speeding up 6-DoF Grasp Sampling with Quality-Diversitycited by 4
  12. 2024Diversifying Policy Behaviors with Extrinsic Behavioral Curiositycited by 4
12 more
  1. 2024Imitation from Diverse Behaviors: Wasserstein Quality Diversity Imitation Learning with Single-Step Archive Explorationcited by 4
  2. 2025AutoQD: Automatic Discovery of Diverse Behaviors with Quality-Diversity Optimizationcited by 3
  3. 2023Density Descent for Diversity Optimizationcited by 2
  4. 2024Algorithmic Scenario Generation as Quality Diversity Optimizationcited by 1
  5. 2024Preference-Conditioned Gradient Variations for Multi-Objective Quality-Diversitycited by 1
  6. 2025Algorithmic Prompt Generation for Diverse Human-like Teaming and Communication with Large Language Modelscited by 1
  7. 2025Soft Quality-Diversity Optimizationcited by 1
  8. 2026Discount Model Search for Quality Diversity Optimization in High-Dimensional Measure Spacescited by 1
  9. 2026Optimization of Edge Directions and Weights for Mixed Guidance Graphs in Lifelong Multi-Agent Path Findingcited by 1
  10. 2025Placeit! A Framework for Learning Robot Object Placement Skillscited by 0
  11. 2026Quality-Diversity Optimization as Multi-Objective Optimizationcited by 0
  12. 2026Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolutioncited by 0