A novel reinforcement learning-based method for structure optimization

被引:0
|
作者
Mei, Zijian [1 ,2 ]
Yang, Zhouwang [3 ,4 ]
Chen, Jingrun [2 ,5 ]
机构
[1] Univ Sci & Technol China, Sch Artificial Intelligence & Data Sci, Suzhou, Peoples R China
[2] Univ Sci & Technol China, Suzhou Inst Adv Res, Suzhou, Peoples R China
[3] Univ Sci & Technol China, Sch Math Sci, Hefei, Peoples R China
[4] Univ Sci & Technol China, Sch Artificial Intelligence & Data Sci, Hefei, Peoples R China
[5] Univ Sci & Technol China, Sch Math Sci, Suzhou, Peoples R China
基金
国家重点研发计划;
关键词
Structure optimization; reinforcement learning; Monte Carlo tree search; deep learning; TOPOLOGY OPTIMIZATION; DESIGN; SHAPE;
D O I
10.1080/0305215X.2024.2411412
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
With the rapid development of deep learning technology, Reinforcement Learning (RL) has garnered considerable acclaim within the realm of structural optimization owing to its excellent exploration mechanism. However, the widespread application of RL in this field is limited owing to the excessive number of iterations required to converge and the expensive computational cost it brings. To address these challenges, this article presents a novel RL framework for structural optimization, combining Monte Carlo tree search with the proximal policy optimization method, called LMPOM. The key contributions of LMPOM encompass: (1) an enhanced Monte Carlo tree search strategy for partitioning the hybrid design space; (2) a strategy for adaptively updating surrogate models to reduce simulation costs; and (3) the introduction of a novel termination condition for the RL algorithms. Through tests on three benchmark problems, compared with previous RL algorithms, LMPOM consistently shows fewer iterations and better optimization results.
引用
收藏
页数:20
相关论文
共 50 条
  • [1] Evolutionary Reinforcement Learning-based Optimization Method for Ship Concept Schemes
    Sun, Kaiwei
    Yang, Meng
    Wang, Zhicheng
    Zhou, Ta
    2024 INTERNATIONAL CONFERENCE ON ELECTRONIC ENGINEERING AND INFORMATION SYSTEMS, EEISS 2024, 2024, : 47 - 54
  • [2] A novel reinforcement learning-based reptile search algorithm for solving optimization problems
    Mohamed Ghetas
    Mohamed Issa
    Neural Computing and Applications, 2024, 36 : 533 - 568
  • [3] A novel reinforcement learning-based reptile search algorithm for solving optimization problems
    Ghetas, Mohamed
    Issa, Mohamed
    NEURAL COMPUTING & APPLICATIONS, 2023, 36 (2): : 533 - 568
  • [4] A deep reinforcement learning-based optimization method for vibration suppression of articulated robots
    Zhang, Tie
    Chu, Hubo
    Zou, Yanbiao
    Liu, Tao
    ENGINEERING OPTIMIZATION, 2023, 55 (07) : 1189 - 1206
  • [5] Deep Reinforcement Learning-based Power Distribution Network Structure Design Optimization Method for High Bandwidth Memory Interposer
    Lee, Seonghi
    Kim, Hyunwoong
    Song, Kyunghwan
    Kim, Jongwook
    Park, Dongryul
    Ahn, Jangyong
    Kim, Keunwoo
    Ahn, Seungyoung
    IEEE 30TH CONFERENCE ON ELECTRICAL PERFORMANCE OF ELECTRONIC PACKAGING AND SYSTEMS (EPEPS 2021), 2021,
  • [6] A Novel Deep Reinforcement Learning-Based Current Control Method for Direct Matrix Converters
    Li, Yao
    Qiu, Lin
    Liu, Xing
    Ma, Jien
    Zhang, Jian
    Fang, Youtong
    ENERGIES, 2023, 16 (05)
  • [7] A Novel Deep Reinforcement Learning-based Automatic Stock Trading Method and a Case Study
    He, Youzhang
    Yang, Yuchen
    Li, Yihe
    Sun, Peng
    2022 IEEE 1ST GLOBAL EMERGING TECHNOLOGY BLOCKCHAIN FORUM: BLOCKCHAIN & BEYOND, IGETBLOCKCHAIN, 2022,
  • [8] A reinforcement learning-based communication topology in particle swarm optimization
    Xu, Yue
    Pi, Dechang
    NEURAL COMPUTING & APPLICATIONS, 2020, 32 (14): : 10007 - 10032
  • [9] A reinforcement learning-based communication topology in particle swarm optimization
    Yue Xu
    Dechang Pi
    Neural Computing and Applications, 2020, 32 : 10007 - 10032
  • [10] Reinforcement Learning-Based Insulin Injection Time And Dosages Optimization
    Wang, Zihao
    Xie, Zhiqiang
    Tu, Enmei
    Zhong, Alex
    Liu, Yingying
    Ding, Jichang
    Yang, Jie
    2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,