mlsanityData to 14 Oct 2026

Advancing CMA-ES with Learning-Based Cooperative Coevolution for Scalable Optimization

arXiv 2504.17578 ↗First posted 24 Apr 2025cs.LG cs.NEcited by 4

On the map: Deep reinforcement learning methods → RL for games and combinatorial optimization

Abstract (arXiv)

Recent research in Cooperative Coevolution~(CC) have achieved promising progress in solving large-scale global optimization problems. However, existing CC paradigms have a primary limitation in that they require deep expertise for selecting or designing effective variable decomposition strategies. Inspired by advancements in Meta-Black-Box Optimization, this paper introduces LCC, a pioneering learning-based cooperative coevolution framework that dynamically schedules decomposition strategies during optimization processes. The decomposition strategy selector is parameterized through a neural network, which processes a meticulously crafted set of optimization status features to determine the optimal strategy for each optimization step. The network is trained via the Proximal Policy Optimization method in a reinforcement learning manner across a collection of representative problems, aiming to maximize the expected optimization performance. Extensive experimental results demonstrate that LCC not only offers certain advantages over state-of-the-art baselines in terms of optimization effectiveness and resource consumption, but it also exhibits promising transferability towards unseen problems.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods. Builds on 27 of its 86 references that are in the map. First posted on arXiv 24 Apr 2025.

Builds on

27 of 86 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025Reinforcement Learning-based Self-adaptive Differential Evolution through Automated Landscape Feature Learning23 Mar
  2. 2025Surrogate Learning in Meta-Black-Box Optimization: A Preliminary Study23 Mar
  3. 2024ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement Learning10 Dec
  4. 2024RLEMMO: Evolutionary Multimodal Optimization Assisted By Deep Reinforcement Learning12 Apr
  5. 2024Auto-configuring Exploration-Exploitation Tradeoff in Evolutionary Computation via Deep Reinforcement Learning12 Apr
  6. 2024Deep Reinforcement Learning for Dynamic Algorithm Selection: A Proof-of-Principle Study on Differential Evolution4 Mar
  7. 2024Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms22 Jan

Other references · 20

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018A Survey Of Methods For Explaining Black Box Modelscited by 973
  3. 2016The CMA Evolution Strategy: A Tutorialcited by 377
  4. 2017Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learningcited by 150
  5. 2021Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategiescited by 52
  6. 2022Discovering Evolution Strategies via Meta-Black-Box Optimizationcited by 44
  7. 2019Deep Reinforcement Learning Based Parameter Control in Differential Evolutioncited by 38
  8. 2022Multi-agent Dynamic Algorithm Configurationcited by 36
  9. 2023MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learningcited by 36
  10. 2020Neuroevolution in Deep Neural Networks: Current Trends and Future Challengescited by 33
  11. 2021Learning adaptive differential evolution algorithm from optimization experiences by policy gradientcited by 26
  12. 2024Symbol: Generating Flexible Black-Box Optimizers through Symbolic Equation Learningcited by 22
8 more
  1. 2023B2Opt: Learning to Optimize Black-box Optimization with Little Budgetcited by 15
  2. 2024Pretrained Optimization Model for Zero-Shot Black Box Optimizationcited by 13
  3. 2022MMES: Mixture Model based Evolution Strategy for Large-Scale Optimizationcited by 9
  4. 2025MetaDE: Evolving Differential Evolution by Differential Evolutioncited by 9
  5. 2015LM-CMA: an Alternative to L-BFGS for Large Scale Black-box Optimizationcited by 5
  6. 2025Accurate Peak Detection in Multimodal Optimization via Approximated Landscape Learningcited by 5
  7. 2024An Enhanced Differential Grouping Method for Large-Scale Overlapping Problemscited by 3
  8. 2025A Novel Two-Phase Cooperative Co-evolution Framework for Large-Scale Global Optimization with Complex Overlappingcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025MetaBox-v2: A Unified Benchmark Platform for Meta-Black-Box Optimizationcited by 9
  2. 2026Detect and Act: Automated Dynamic Optimizer through Meta-Black-Box Optimizationcited by 1
  3. 2026A Learning-Based Cooperative Coevolution Framework for Heterogeneous Large-Scale Global Optimizationcited by 1
  4. 2026Neural Operator-enabled Topology-informed Evolutionary Strategy for PDE-Constrained Optimizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Evolutionary Reinforcement Learning via Cooperative Coevolution
  2. 2026Cooperative Coevolution for Resource-Constrained Agentic LLM Post-Training
  3. 2026Descent-Guided Policy Gradient for Scalable Cooperative Multi-Agent Learning
  4. 2026Breaking textitWinner-Takes-All: Cooperative Policy Optimization Improves Diverse LLM Reasoning
  5. 2024Dynamic Co-Optimization Compiler: Leveraging Multi-Agent Reinforcement Learning for Enhanced DNN Accelerator Performance
  6. 2024Toward Automated Algorithm Design: A Survey and Practical Guide to Meta-Black-Box-Optimization
  7. 2024Potentially Optimal Joint Actions Recognition for Cooperative Multi-Agent Reinforcement Learning
  8. 2025Learn to Relax with Large Language Models: Solving Constraint Optimization Problems via Bidirectional Coevolution