Hyper-heuristic approach: automatically designing adaptive mutation operators for evolutionary programming

Hong, Libin; Woodward, John R.; Özcan, Ender; Liu, Fuchang

Abstract

Genetic programming (GP) automatically designs programs. Evolutionary programming (EP) is a real-valued global optimisation method. EP uses a probability distribution as a mutation operator, such as Gaussian, Cauchy, or Lévy distribution. This study proposes a hyper-heuristic approach that employs GP to automatically design different mutation operators for EP. At each generation, the EP algorithm can adaptively explore the search space according to historical information. The experimental results demonstrate that the EP with adaptive mutation operators, designed by the proposed hyper-heuristics, exhibits improved performance over other EP versions (both manually and automatically designed). Many researchers in evolutionary computation advocate adaptive search operators (which do adapt over time) over non-adaptive operators (which do not alter over time). The core motive of this study is that we can automatically design adaptive mutation operators that outperform automatically designed non-adaptive mutation operators.

Citation

Hong, L., Woodward, J. R., Özcan, E., & Liu, F. (2021). Hyper-heuristic approach: automatically designing adaptive mutation operators for evolutionary programming. Complex and Intelligent Systems, 7(6), 3135-3163. https://doi.org/10.1007/s40747-021-00507-6

• Journal Article Type: Article
• Acceptance Date: Aug 12, 2021
• Online Publication Date: Aug 28, 2021
• Publication Date: Dec 1, 2021
• Deposit Date: Dec 2, 2021
• Publicly Available Date: Dec 13, 2021
• Journal: Complex and Intelligent Systems
• Print ISSN: 2199-4536
• Electronic ISSN: 2198-6053
• Publisher: Springer Science and Business Media LLC
• Peer Reviewed: Peer Reviewed
• Volume: 7
• Issue: 6
• Pages: 3135-3163
• DOI: https://doi.org/10.1007/s40747-021-00507-6
• Keywords: General Earth and Planetary Sciences; General Environmental Science
• Public URL: https://nottingham-repository.worktribe.com/output/6847178
• Publisher URL: https://link.springer.com/article/10.1007/s40747-021-00507-6