Reinforcement Learning-Based Hybrid Multi-Objective Optimization Algorithm Design

被引:5
|
作者
Palm, Herbert [1 ]
Arndt, Lorin [1 ]
机构
[1] Univ Appl Sci, Syst Engn Lab, Lothstr 64, D-80335 Munich, Germany
关键词
multi-objective optimization; complex systems; Pareto front; hybrid search algorithms; reinforcement learning; intelligent agent; COMPLEXITY;
D O I
10.3390/info14050299
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The multi-objective optimization (MOO) of complex systems remains a challenging task in engineering domains. The methodological approach of applying MOO algorithms to simulation-enabled models has established itself as a standard. Despite increasing in computational power, the effectiveness and efficiency of such algorithms, i.e., their ability to identify as many Pareto-optimal solutions as possible with as few simulation samples as possible, plays a decisive role. However, the question of which class of MOO algorithms is most effective or efficient with respect to which class of problems has not yet been resolved. To tackle this performance problem, hybrid optimization algorithms that combine multiple elementary search strategies have been proposed. Despite their potential, no systematic approach for selecting and combining elementary Pareto search strategies has yet been suggested. In this paper, we propose an approach for designing hybrid MOO algorithms that uses reinforcement learning (RL) techniques to train an intelligent agent for dynamically selecting and combining elementary MOO search strategies. We present both the fundamental RL-Based Hybrid MOO (RLhybMOO) methodology and an exemplary implementation applied to mathematical test functions. The results indicate a significant performance gain of intelligent agents over elementary and static hybrid search strategies, highlighting their ability to effectively and efficiently select algorithms.
引用
收藏
页数:13
相关论文
共 50 条
  • [1] Multi-objective optimization design of a compliant microgripper based on hybrid teaching learning-based optimization algorithm
    Nhat Linh Ho
    Thanh-Phong Dao
    Ngoc Le Chau
    Shyh-Chour Huang
    Microsystem Technologies, 2019, 25 : 2067 - 2083
  • [2] Multi-objective optimization design of a compliant microgripper based on hybrid teaching learning-based optimization algorithm
    Nhat Linh Ho
    Thanh-Phong Dao
    Ngoc Le Chau
    Huang, Shyh-Chour
    MICROSYSTEM TECHNOLOGIES-MICRO-AND NANOSYSTEMS-INFORMATION STORAGE AND PROCESSING SYSTEMS, 2019, 25 (05): : 2067 - 2083
  • [3] Reinforcement learning-based differential evolution algorithm for constrained multi-objective optimization problems
    Yu, Xiaobing
    Xu, Pingping
    Wang, Feng
    Wang, Xuming
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 131
  • [4] An Improved Multi-objective Optimization Algorithm Based on Reinforcement Learning
    Liu, Jun
    Zhou, Yi
    Qiu, Yimin
    Li, Zhongfeng
    ADVANCES IN SWARM INTELLIGENCE, ICSI 2022, PT I, 2022, : 501 - 513
  • [5] A reinforcement learning-based multi-objective optimization in an interval and dynamic environment
    Xu, Yue
    Song, Yuxuan
    Pi, Dechang
    Chen, Yang
    Qin, Shuo
    Zhang, Xiaoge
    Yang, Shengxiang
    KNOWLEDGE-BASED SYSTEMS, 2023, 280
  • [6] A novel multi-state reinforcement learning-based multi-objective evolutionary algorithm
    Wang, Jing
    Zheng, Yuxin
    Zhang, Ziyun
    Peng, Hu
    Wang, Hui
    INFORMATION SCIENCES, 2025, 688
  • [7] A Deep Reinforcement Learning-Based Algorithm for Multi-Objective Agricultural Site Selection and Logistics Optimization Problem
    Liu, Huan
    Zhang, Jizhe
    Zhou, Zhao
    Dai, Yongqiang
    Qin, Lijing
    Applied Sciences (Switzerland), 14 (18):
  • [8] A Deep Reinforcement Learning-Based Algorithm for Multi-Objective Agricultural Site Selection and Logistics Optimization Problem
    Liu, Huan
    Zhang, Jizhe
    Zhou, Zhao
    Dai, Yongqiang
    Qin, Lijing
    APPLIED SCIENCES-BASEL, 2024, 14 (18):
  • [9] Reinforcement learning-based multi-objective differential evolution algorithm for feature selection
    Yu, Xiaobing
    Hu, Zhengpeng
    Luo, Wenguan
    Xue, Yu
    INFORMATION SCIENCES, 2024, 661
  • [10] Multi-objective reinforcement learning-based approach for pressurized water reactor optimization
    Seurin, Paul
    Shirvan, Koroush
    ANNALS OF NUCLEAR ENERGY, 2024, 205