Partnering Strategies for Fitness Evaluation in a Pyramidal Evolutionary Algorithm

This paper combines the idea of a hierarchical distributed genetic algorithm with different inter-agent partnering strategies. Cascading clusters of sub-populations are built from bottom up, with higher-level sub-populations optimising larger parts of the problem. Hence higher-level sub-populations...

Full description

Bibliographic Details
Main Authors: Aickelin, Uwe, Bull, Larry
Format: Conference or Workshop Item
Published: 2002
Online Access:https://eprints.nottingham.ac.uk/633/
_version_ 1848790449910710272
author Aickelin, Uwe
Bull, Larry
author_facet Aickelin, Uwe
Bull, Larry
author_sort Aickelin, Uwe
building Nottingham Research Data Repository
collection Online Access
description This paper combines the idea of a hierarchical distributed genetic algorithm with different inter-agent partnering strategies. Cascading clusters of sub-populations are built from bottom up, with higher-level sub-populations optimising larger parts of the problem. Hence higher-level sub-populations search a larger search space with a lower resolution whilst lower-level sub-populations search a smaller search space with a higher resolution. The effects of different partner selection schemes for (sub-)fitness evaluation purposes are examined for two multiple-choice optimisation problems. It is shown that random partnering strategies perform best by providing better sampling and more diversity.
first_indexed 2025-11-14T18:12:48Z
format Conference or Workshop Item
id nottingham-633
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T18:12:48Z
publishDate 2002
recordtype eprints
repository_type Digital Repository
spelling nottingham-6332020-05-04T20:32:14Z https://eprints.nottingham.ac.uk/633/ Partnering Strategies for Fitness Evaluation in a Pyramidal Evolutionary Algorithm Aickelin, Uwe Bull, Larry This paper combines the idea of a hierarchical distributed genetic algorithm with different inter-agent partnering strategies. Cascading clusters of sub-populations are built from bottom up, with higher-level sub-populations optimising larger parts of the problem. Hence higher-level sub-populations search a larger search space with a lower resolution whilst lower-level sub-populations search a smaller search space with a higher resolution. The effects of different partner selection schemes for (sub-)fitness evaluation purposes are examined for two multiple-choice optimisation problems. It is shown that random partnering strategies perform best by providing better sampling and more diversity. 2002 Conference or Workshop Item PeerReviewed Aickelin, Uwe and Bull, Larry (2002) Partnering Strategies for Fitness Evaluation in a Pyramidal Evolutionary Algorithm. In: Genetic and Evolutionary Computation Conference, 2002, New York, USA.
spellingShingle Aickelin, Uwe
Bull, Larry
Partnering Strategies for Fitness Evaluation in a Pyramidal Evolutionary Algorithm
title Partnering Strategies for Fitness Evaluation in a Pyramidal Evolutionary Algorithm
title_full Partnering Strategies for Fitness Evaluation in a Pyramidal Evolutionary Algorithm
title_fullStr Partnering Strategies for Fitness Evaluation in a Pyramidal Evolutionary Algorithm
title_full_unstemmed Partnering Strategies for Fitness Evaluation in a Pyramidal Evolutionary Algorithm
title_short Partnering Strategies for Fitness Evaluation in a Pyramidal Evolutionary Algorithm
title_sort partnering strategies for fitness evaluation in a pyramidal evolutionary algorithm
url https://eprints.nottingham.ac.uk/633/