mlsanityData to 14 Oct 2026

Graph-Supported Dynamic Algorithm Configuration for Multi-Objective Combinatorial Optimization

arXiv 2505.16471 ↗First posted 22 May 2025cs.NE cs.LGcited by 0

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

Abstract (arXiv)

Deep reinforcement learning (DRL) has been widely used for dynamic algorithm configuration, particularly in evolutionary computation, which benefits from the adaptive update of parameters during the algorithmic execution. However, applying DRL to algorithm configuration for multi-objective combinatorial optimization (MOCO) problems remains relatively unexplored. This paper presents a novel graph neural network (GNN) based DRL to configure multi-objective evolutionary algorithms. We model the dynamic algorithm configuration as a Markov decision process, representing the convergence of solutions in the objective space by a graph, with their embeddings learned by a GNN to enhance the state representation. Experiments on diverse MOCO challenges indicate that our method outperforms traditional and DRL-based algorithm configuration methods in terms of efficacy and adaptability. It also exhibits advantageous generalizability across objective types and problem sizes, and applicability to different evolutionary computation methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods. Builds on 14 of its 42 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

14 of 42 references.

References · 14

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  4. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 503
  5. 2021SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimizationcited by 230
  6. 2022Pareto Set Learning for Neural Multi-objective Combinatorial Optimizationcited by 56
  7. 2022Automated Dynamic Algorithm Configurationcited by 39
  8. 2019Deep Reinforcement Learning Based Parameter Control in Differential Evolutioncited by 38
  9. 2022Multi-agent Dynamic Algorithm Configurationcited by 36
  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
2 more
  1. 2023Job Shop Scheduling Benchmark: Environments and Instances for Learning and Non-learning Methodscited by 12
  2. 2014A MILP model for an extended version of the Flexible Job Shop Problemcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Deep Reinforcement Learning for Dynamic Algorithm Selection: A Proof-of-Principle Study on Differential Evolution
  2. 2025Heuristics for Combinatorial Optimization via Value-based Reinforcement Learning: A Unified Framework and Analysis
  3. 2026When does learning pay off? A study on DRL-based dynamic algorithm configuration for carbon-aware scheduling
  4. 2024Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying Perspective
  5. 2025Synergizing Reinforcement Learning and Genetic Algorithms for Neural Combinatorial Optimization
  6. 2025Preference-Driven Multi-Objective Combinatorial Optimization with Conditional Computation
  7. 2025ASAP: Exploiting the Satisficing Generalization Edge in Neural Combinatorial Optimization
  8. 2025Deep Reinforcement Learning for Dynamic Algorithm Configuration: A Case Study on Optimizing OneMax with the (1+(λ,λ))-GA