Coevolutionary strategies at the collective level for improved generalism
Coevolutionary strategies at the collective level for improved generalism
In many complex practical optimization cases, the dominant characteristics of the problem are often not known prior. Therefore, there is a need to develop general solvers as it is not always possible to tailor a specialized approach to each application. The previously developed multilevel selection genetic algorithm (MLSGA) already shows good performance on a range of problems due to its diversity-first approach, which is rare among evolutionary algorithms. To increase the generality of its performance, this paper proposes utilization of multiple distinct evolutionary strategies simultaneously, similarly to algorithm selection, but with coevolutionary mechanisms between the subpopulations. This distinctive approach to coevolution provides less regular communication between subpopulations with competition between collectives rather than individuals. This encourages the collectives to act more independently creating a unique subregional search, leading to the development of coevolutionary MLSGA (cMLSGA). To test this methodology, nine genetic algorithms are selected to generate several variants of cMLSGA, which incorporates these approaches at the individual level. The mechanisms are tested on 100 different functions and benchmarked against the 9 state-of-the-art competitors to evaluate the generality of each approach. The results show that the diversity divergence in the principles of working of the selected coevolutionary approaches is more important than their individual performances. The proposed methodology has the most uniform performance on the divergent problem types, from across the tested state of the art, leading to an algorithm more likely to solve complex problems with limited knowledge about the search space, but is outperformed by more specialized solvers on simpler benchmarking studies.
Coevolutionary, genetic algorithms, multilevel selection, multiobjective optimization
Sobey, Adam James
e850606f-aa79-4c99-8682-2cfffda3cd28
Grudniewski, Przemyslaw Andrzej
30349b11-4667-41d6-9b45-587c46254a2f
6 February 2023
Sobey, Adam James
e850606f-aa79-4c99-8682-2cfffda3cd28
Grudniewski, Przemyslaw Andrzej
30349b11-4667-41d6-9b45-587c46254a2f
Sobey, Adam James and Grudniewski, Przemyslaw Andrzej
(2023)
Coevolutionary strategies at the collective level for improved generalism.
Data-Centric Engineering, 4 (2), [e6].
(doi:10.1017/dce.2023.1).
Abstract
In many complex practical optimization cases, the dominant characteristics of the problem are often not known prior. Therefore, there is a need to develop general solvers as it is not always possible to tailor a specialized approach to each application. The previously developed multilevel selection genetic algorithm (MLSGA) already shows good performance on a range of problems due to its diversity-first approach, which is rare among evolutionary algorithms. To increase the generality of its performance, this paper proposes utilization of multiple distinct evolutionary strategies simultaneously, similarly to algorithm selection, but with coevolutionary mechanisms between the subpopulations. This distinctive approach to coevolution provides less regular communication between subpopulations with competition between collectives rather than individuals. This encourages the collectives to act more independently creating a unique subregional search, leading to the development of coevolutionary MLSGA (cMLSGA). To test this methodology, nine genetic algorithms are selected to generate several variants of cMLSGA, which incorporates these approaches at the individual level. The mechanisms are tested on 100 different functions and benchmarked against the 9 state-of-the-art competitors to evaluate the generality of each approach. The results show that the diversity divergence in the principles of working of the selected coevolutionary approaches is more important than their individual performances. The proposed methodology has the most uniform performance on the divergent problem types, from across the tested state of the art, leading to an algorithm more likely to solve complex problems with limited knowledge about the search space, but is outperformed by more specialized solvers on simpler benchmarking studies.
Text
coevolutionary-strategies-at-the-collective-level
- Version of Record
More information
Accepted/In Press date: 13 January 2023
Published date: 6 February 2023
Additional Information:
Funding Information:
This research was sponsored by Lloyds Register Foundation. The funder had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
Publisher Copyright:
© The Author(s), 2023. Published by Cambridge University Press.
Keywords:
Coevolutionary, genetic algorithms, multilevel selection, multiobjective optimization
Identifiers
Local EPrints ID: 475616
URI: http://eprints.soton.ac.uk/id/eprint/475616
ISSN: 2632-6736
PURE UUID: c5a62459-9509-45c0-b1d9-6bb3327e9d11
Catalogue record
Date deposited: 22 Mar 2023 17:44
Last modified: 06 Jun 2024 01:45
Export record
Altmetrics
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
