Adaptive operator selection with dueling deep Q-network for evolutionary multi-objective optimization

doi:10.1016/j.neucom.2024.127491

2024-05-01

PRE

Shihong Yin

Zhengrong Xiang *

DOI：10.1016/j.neucom.2024.127491

原文链接

原文求助

摘要

En 中文

Adaptive operator selection is an online method that automatically adjusts the application rate of different operators based on their actual performance. This paper proposes an adaptive operator selection paradigm based on dueling deep Q -network (DDQN), aiming to improve the training efficiency of the Q -network for solving multi -objective optimization problems. The Q -network is decomposed into state value and action advantage networks, allowing the agent to learn state values more frequently and accurately. A novel state space and reward mechanism are designed to adapt to the characteristics of evolutionary multi -objective optimization. Combining adaptive operator selection with a multi -objective evolutionary algorithm with adaptive weights (AdaW), an AdaW-DDQN algorithm with high adaptability is proposed. Experimental results on three complex benchmark suites demonstrate that the proposed adaptive operator selection paradigm significantly improves the performance of multi -objective optimization algorithms. The AdaW-DDQN algorithm provides an effective and efficient solution for solving multi -objective optimization problems.

Keyword:

Multi -objective optimization

Adaptive operator selection

Dueling deep Q -network

Reinforcement learning

Evolutionary algorithm

期刊

Neurocomputing

IF:

6.5

论文数:

2.5W

被引数:

6.5W

机构

暂无机构信息

引用论文

Bacterial Rhodopsin: Evidence for a New Type of Phototrophy in the Sea

Science

IF0

2000-09-15

PREAI

Oded Béjà; L. Aravind; Eugene V. Koonin; Marcelino T. Suzuki; Andrew Hadd; Linh P. Nguyen; Stevan B. Jovanovich; Christian M. Gates; Robert A. Feldman; John L. Spudich; Elena N. Spudich; Edward F. DeLong

Optimal consensus of a class of discrete-time linear multi-agent systems via value iteration with guaranteed admissibility 通过具有保证可容许性的值迭代，一类离散时间线性多智能体系统的最佳一致性

NEUROCOMPUTING

IF6.5

2023-01-01

PREAI

Li, Pingchuan; Zou, Wencheng; Guo, Jian; Xiang, Zhengrong

PlatEMO: A MATLAB Platform for Evolutionary Multi-Objective Optimization PlatEMO: 用于进化多目标优化的MATLAB平台

IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE

IF11.2

2017-11-01

1.6K