Skip to main navigation Skip to search Skip to main content

Hybrid Modified Chimp Optimization Algorithm and Reinforcement Learning for Global Numeric Optimization

  • Amman Arab University
  • Ho Chi Minh City Open University

Research output: Contribution to journal › Article › peer-review

26 Scopus citations

Abstract

Chimp Optimization Algorithm (ChOA) is one of the most efficient recent optimization algorithms, which proved its ability to deal with different problems in various do- mains. However, ChOA suffers from the weakness of the local search technique which leads to a loss of diversity, getting stuck in a local minimum, and procuring premature convergence. In response to these defects, this paper proposes an improved ChOA algorithm based on using Opposition-based learning (OBL) to enhance the choice of better solutions, written as OChOA. Then, utilizing Reinforcement Learning (RL) to improve the local research technique of OChOA, called RLOChOA. This way effectively avoids the algorithm falling into local optimum. The performance of the proposed RLOChOA algorithm is evaluated using the Friedman rank test on a set of CEC 2015 and CEC 2017 benchmark functions problems and a set of CEC 2011 real-world problems. Numerical results and statistical experiments show that RLOChOA provides better solution quality, convergence accuracy and stability compared with other state-of-the-art algorithms.

Original languageEnglish
Pages (from-to)2896-2915
Number of pages20
JournalJournal of Bionic Engineering
Volume20
Issue number6
DOIs
StatePublished - Nov 2023

Keywords

  • CEC 2011 real-world problems
  • CEC 2015 and CEC 2017 benchmark functions problems
  • Chimp optimization algorithm
  • Disruption operator
  • Opposition-based learning
  • Reinforcement learning

Fingerprint

Dive into the research topics of 'Hybrid Modified Chimp Optimization Algorithm and Reinforcement Learning for Global Numeric Optimization'. Together they form a unique fingerprint.

Cite this