ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Hongshu, Ma, Zeyuan, Chen, Jiacheng, Ma, Yining, Cao, Zhiguang, Zhang, Xinglin, Gong, Yue-Jiao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912157885530112
author Guo, Hongshu
Ma, Zeyuan
Chen, Jiacheng
Ma, Yining
Cao, Zhiguang
Zhang, Xinglin
Gong, Yue-Jiao
author_facet Guo, Hongshu
Ma, Zeyuan
Chen, Jiacheng
Ma, Yining
Cao, Zhiguang
Zhang, Xinglin
Gong, Yue-Jiao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_07507
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement Learning
Guo, Hongshu
Ma, Zeyuan
Chen, Jiacheng
Ma, Yining
Cao, Zhiguang
Zhang, Xinglin
Gong, Yue-Jiao
Machine Learning
Neural and Evolutionary Computing
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.
title ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement Learning
topic Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2412.07507