mlsanityData to 14 Oct 2026

Multi-agent Dynamic Algorithm Configuration

arXiv 2210.06835 ↗First posted 13 Oct 2022cs.LG cs.AI cs.MAcited by 36

Not on the map. Why?

Abstract (arXiv)

Automated algorithm configuration relieves users from tedious, trial-and-error tuning tasks. A popular algorithm configuration tuning paradigm is dynamic algorithm configuration (DAC), in which an agent learns dynamic configuration policies across instances by reinforcement learning (RL). However, in many complex algorithms, there may exist different types of configuration hyperparameters, and such heterogeneity may bring difficulties for classic DAC which uses a single-agent RL policy. In this paper, we aim to address this issue and propose multi-agent DAC (MA-DAC), with one agent working for one type of configuration hyperparameter. MA-DAC formulates the dynamic configuration of a complex algorithm with multiple types of hyperparameters as a contextual multi-agent Markov decision process and solves it by a cooperative multi-agent RL (MARL) algorithm. To instantiate, we apply MA-DAC to a well-known optimization algorithm for multi-objective optimization problems. Experimental results show the effectiveness of MA-DAC in not only achieving superior performance compared with other configuration tuning approaches based on heuristic rules, multi-armed bandits, and single-agent RL, but also being capable of generalizing to different problem classes. Furthermore, we release the environments in this paper as a benchmark for testing MARL algorithms, with the hope of facilitating the application of MARL.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). Builds on 28 of its 73 references that are in the map. First posted on arXiv 13 Oct 2022.

Builds on

28 of 73 references.

References · 28

  1. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  2. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 708
  3. 2019The StarCraft Multi-Agent Challengecited by 597
  4. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 567
  5. 2019QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learningcited by 379
  6. 2020PettingZoo: Gym for Multi-Agent Reinforcement Learningcited by 220
  7. 2020Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Taskscited by 212
  8. 2015Multiagent Cooperation and Competition with Deep Reinforcement Learningcited by 184
  9. 2018A Survey and Critique of Multiagent Deep Reinforcement Learningcited by 177
  10. 2019A Review of Cooperative Multi-Agent Deep Reinforcement Learningcited by 147
  11. 2021Tianshou: a Highly Modularized Deep Reinforcement Learning Librarycited by 143
  12. 2019Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learningcited by 93
16 more
  1. 2014ParamILS: An Automatic Algorithm Configuration Frameworkcited by 89
  2. 2020NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Searchcited by 76
  3. 2017MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligencecited by 71
  4. 2021Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networkscited by 54
  5. 2022Towards a Standardised Performance Evaluation Protocol for Cooperative MARLcited by 49
  6. 2017PlatEMO: A MATLAB Platform for Evolutionary Multi-Objective Optimizationcited by 41
  7. 2020Fair Algorithms for Multi-Agent Multi-Armed Banditscited by 41
  8. 2022Automated Dynamic Algorithm Configurationcited by 39
  9. 2019Deep Reinforcement Learning Based Parameter Control in Differential Evolutioncited by 38
  10. 2021DACBench: A Benchmark Library for Dynamic Algorithm Configurationcited by 28
  11. 2021Learning adaptive differential evolution algorithm from optimization experiences by policy gradientcited by 26
  12. 2020Learning Heuristic Selection with Dynamic Algorithm Configurationcited by 21
  13. 2020Heterogeneous Multi-Agent Reinforcement Learning for Unknown Environment Mappingcited by 13
  14. 2022Theory-inspired Parameter Control Benchmarks for Dynamic Algorithm Configurationcited by 11
  15. 2021Decomposition Multi-Objective Evolutionary Optimization: From State-of-the-Art to Future Opportunitiescited by 4
  16. 2017What Weights Work for You? Adapting Weights for Any Pareto Front Shape in Decomposition-based Evolutionary Multi-Objective Optimisationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 7; 2025: 16; 2026: 5.

36 papers.

Sort:

By area:

  1. 2024Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithmscited by 26
  2. 2024Deep Reinforcement Learning for Dynamic Algorithm Selection: A Proof-of-Principle Study on Differential Evolutioncited by 24
  3. 2024Toward Automated Algorithm Design: A Survey and Practical Guide to Meta-Black-Box-Optimizationcited by 24
  4. 2025Pareto Set Learning for Multi-Objective Reinforcement Learningcited by 20
  5. 2023Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackerscited by 15
  6. 2024Reinforced In-Context Black-Box Optimizationcited by 14
  7. 2023Multi-agent Continual Coordination via Progressive Task Contextualizationcited by 11
  8. 2024Neural Exploratory Landscape Analysis for Meta-Black-Box-Optimizationcited by 10
  9. 2025MetaBox-v2: A Unified Benchmark Platform for Meta-Black-Box Optimizationcited by 9
  10. 2023Self-Motivated Multi-Agent Explorationcited by 7
  11. 2023Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generationcited by 6
  12. 2024Open Ad Hoc Teamwork with Cooperative Game Theorycited by 6
24 more
  1. 2023Using Automated Algorithm Configuration for Parameter Controlcited by 5
  2. 2025DesignX: Human-Competitive Algorithm Designer for Black-Box Optimizationcited by 5
  3. 2025BBOPlace-Bench: Benchmarking Black-Box Optimization for Chip Placementcited by 5
  4. 2025Advancing CMA-ES with Learning-Based Cooperative Coevolution for Scalable Optimizationcited by 4
  5. 2023Robust Multi-agent Communication via Multi-view Message Certificationcited by 3
  6. 2025Sequential Multi-Agent Dynamic Algorithm Configurationcited by 3
  7. 2023Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learningcited by 2
  8. 2025Reliable and Efficient Multi-Agent Coordination via Graph Neural Network Variational Autoencoderscited by 2
  9. 2025Large Language Model-Driven Surrogate-Assisted Evolutionary Algorithm for Expensive Optimizationcited by 2
  10. 2024CuDA2: An approach for Incorporating Traitor Agents into Cooperative Multi-Agent Systemscited by 1
  11. 2025Adaptive and Robust DBSCAN with Multi-agent Reinforcement Learningcited by 1
  12. 2025Multi-parameter Control for the (1+(λ,λ))-GA on OneMax via Deep Reinforcement Learningcited by 1
  13. 2025Toward Adaptable Multi-Agent Reinforcement Learning: An Assumption-Aware Reviewcited by 1
  14. 2025Learning Where, What and How to Transfer: A Multi-Role Reinforcement Learning Approach for Evolutionary Multitaskingcited by 1
  15. 2026Meta-Black-Box Optimization with Ensemble Surrogate Modeling for Robustness-Accuracy Trade-off within SAEAcited by 1
  16. 2023Hybrid Algorithm Selection and Hyperparameter Tuning on Distributed Machine Learning Resources: A Hierarchical Agent-based Approachcited by 0
  17. 2025Multi-Agent Inverse Q-Learning from Demonstrationscited by 0
  18. 2025Interpreting Graph Inference with Skyline Explanationscited by 0
  19. 2025Graph-Supported Dynamic Algorithm Configuration for Multi-Objective Combinatorial Optimizationcited by 0
  20. 2025From Observations to Parameters: Detecting Changepoint in Nonlinear Dynamics with Simulation-based Inferencecited by 0
  21. 2026Discovering Interpretable Multi-Parameter Control Policies for Evolutionary Algorithms Using Deep Reinforcement Learningcited by 0
  22. 2026NeurGO: Learning to Generate Elite Candidates for Meta-Black-Box Expensive Optimizationcited by 0
  23. 2026Rethinking Learnability in Offline Data-driven Optimizationcited by 0
  24. 2026Hyper Algorithm Design Agent: Evolving Learnable Optimizer from Zerocited by 0