Skip to main navigation Skip to search Skip to main content

Reinforcement learning enhanced zeroth-order optimization for large-scale multiobjective optimization problems

  • Yonglin He
  • , Cheng He*
  • , Zhichao Lu
  • , Ye Tian
  • , Handing Wang
  • , Yinglan Feng
  • , Hongbin Li
  • *Corresponding author for this work

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

Abstract

“The curse of dimensionality” poses a major challenge to the scalability of multiobjective evolutionary algorithms (MOEAs) for large-scale multiobjective optimization problems (LSMOPs). Although existing MOEAs have achieved encouraging performance on problems with hundreds of decision variables, solving higher-dimensional LSMOPs remains computationally demanding. To mitigate these scalability challenges, we propose MOZO, an evolutionary zeroth-order (ZO) optimization method that combines zeroth-order directional estimation with a population-based MOEA backbone. Specifically, MOZO first estimates and aggregates objective-wise ZO gradients to provide search directions in high-dimensional decision spaces. It then refines these directions using acceleration and adaptation modules and embeds them within a population-based evolutionary search process to improve robustness against noisy estimates and objective conflicts. In addition, MOZO incorporates a reinforcement learning mechanism to adaptively configure suitable ZO and MOEA modules during the search process. Experimental results on benchmark LSMOPs with up to 100,000 decision variables demonstrate the effectiveness, efficiency, and scalability of MOZO compared with five state-of-the-art large-scale MOEAs. We further apply MOZO to the fine-tuning of OPT-2.7B and OPT-6.7B large language models on a single GPU, where the results show its practical potential under memory-constrained settings. © 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.
Original languageEnglish
Article number102514
JournalSwarm and Evolutionary Computation
Volume108
Online published25 Aug 2026
DOIs
Publication statusPublished - Sept 2026

Funding

This work was supported by the National Key Research and Development Program of China (No. 2022YFB2403800). The computation is completed in the HPC Platform of Huazhong University of Science and Technology.

Research Keywords

  • Evolutionary computation
  • Large-scale optimization
  • Multiobjective optimization
  • Reinforcement learning
  • Zeroth-order optimization

Fingerprint

Dive into the research topics of 'Reinforcement learning enhanced zeroth-order optimization for large-scale multiobjective optimization problems'. Together they form a unique fingerprint.

Cite this