Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

4-2025

Abstract

Recent advances in Meta-learning for Black-Box Optimization (MetaBBO) have shown the potential of using neural networks to dynamically configure evolutionary algorithms (EAs), enhancing their performance and adaptability across various BBO instances. However, they are often tailored to a specific EA, which limits their generalizability and necessitates retraining or redesigns for different EAs and optimization problems. To address this limitation, we introduce ConfigX, a new paradigm of the MetaBBO framework that is capable of learning a universal configuration agent (model) for boosting diverse EAs. To achieve so, our ConfigX first leverages a novel modularization system that enables the flexible combination of various optimization sub-modules to generate diverse EAs during training. Additionally, we propose a Transformer-based neural network to meta-learn a universal configuration policy through multitask reinforcement learning across a designed joint optimization task space. Extensive experiments verify that, our ConfigX, after large-scale pre-training, achieves robust zero-shot generalization to unseen tasks and outperforms state-of-the-art baselines. Moreover, ConfigX exhibits strong lifelong learning capabilities, allowing efficient adaptation to new tasks through fine-tuning. Our proposed ConfigX represents a significant step toward an automatic, all-purpose configuration agent for EAs.

Keywords

meta-learning, black-box optimization, evolutionary algorithms, algorithm configuration, multitask reinforcement learning, Transformer models, modular optimization, zero-shot generalization, lifelong learning, MetaBBO

Discipline

Artificial Intelligence and Robotics

Research Areas

Intelligent Systems and Optimization

Publication

Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence

Volume

39

First Page

26982

Last Page

26990

Identifier

10.1609/aaai.v39i25.34904

Publisher

Association for the Advancement of Artificial Intelligence

City or Country

Philadelphia

Additional URL

https://doi.org/10.1609/aaai.v39i25.34904

Download

Share

COinS