Genetically programmed learning classifier system
description and results
G. Harrison, and E. Worden. Genetic and Evolutionary Computation Conference
(GECCO2007) workshop program, page 2729--2736. London, United Kingdom, ACM Press, (7-11 July 2007)
Abstract
An agent population can be evolved in a complex
environment to perform various tasks and optimise its
job performance using Learning Classifier System (LCS)
technology. Due to the complexity and knowledge content
of some real-world systems, having the ability to use
genetic programming, GP, to represent the LCS rules
provides a great benefit. Methods have been created to
extend LCS theory into operation across the power-set
of GP-enabled rule content. This system uses a full
bucketbrigade system for GP-LCS learning. Using GP in
the LCS system allows the functions and terminals of
the actual problem environment to be used internally
directly in the rule set, enabling more direct
interpretation of the operation of the LCS system. The
system was designed and built, and underwent
independent testing at an advanced technology research
laboratory. This paper describes the top-level
operation of the system, and includes some of the
results of the testing effort, and performance
figures.
%0 Conference Paper
%1 1274068
%A Harrison, Gregory Anthony
%A Worden, Eric W.
%B Genetic and Evolutionary Computation Conference
(GECCO2007) workshop program
%C London, United Kingdom
%D 2007
%E Yu, Tina
%I ACM Press
%K (GBML), (LCS), agent agent, algorithms, autonomous brigade, bucket classifier computation, evolutionary genetic genetics-based intelligent learning learning, machine programming, reinforcement system
%P 2729--2736
%T Genetically programmed learning classifier system
description and results
%U http://doi.acm.org/10.1145/1274000.1274068
%X An agent population can be evolved in a complex
environment to perform various tasks and optimise its
job performance using Learning Classifier System (LCS)
technology. Due to the complexity and knowledge content
of some real-world systems, having the ability to use
genetic programming, GP, to represent the LCS rules
provides a great benefit. Methods have been created to
extend LCS theory into operation across the power-set
of GP-enabled rule content. This system uses a full
bucketbrigade system for GP-LCS learning. Using GP in
the LCS system allows the functions and terminals of
the actual problem environment to be used internally
directly in the rule set, enabling more direct
interpretation of the operation of the LCS system. The
system was designed and built, and underwent
independent testing at an advanced technology research
laboratory. This paper describes the top-level
operation of the system, and includes some of the
results of the testing effort, and performance
figures.
@inproceedings{1274068,
abstract = {An agent population can be evolved in a complex
environment to perform various tasks and optimise its
job performance using Learning Classifier System (LCS)
technology. Due to the complexity and knowledge content
of some real-world systems, having the ability to use
genetic programming, GP, to represent the LCS rules
provides a great benefit. Methods have been created to
extend LCS theory into operation across the power-set
of GP-enabled rule content. This system uses a full
bucketbrigade system for GP-LCS learning. Using GP in
the LCS system allows the functions and terminals of
the actual problem environment to be used internally
directly in the rule set, enabling more direct
interpretation of the operation of the LCS system. The
system was designed and built, and underwent
independent testing at an advanced technology research
laboratory. This paper describes the top-level
operation of the system, and includes some of the
results of the testing effort, and performance
figures.},
added-at = {2008-06-19T17:35:00.000+0200},
address = {London, United Kingdom},
author = {Harrison, Gregory Anthony and Worden, Eric W.},
biburl = {https://www.bibsonomy.org/bibtex/2b8f30e4323a6f8c85e84b268f78a44e4/brazovayeye},
booktitle = {Genetic and Evolutionary Computation Conference
{(GECCO2007)} workshop program},
editor = {Yu, Tina},
interhash = {d1de44a24c93c0b0a3dd962b4f54abc7},
intrahash = {b8f30e4323a6f8c85e84b268f78a44e4},
isbn13 = {978-1-59593-698-1},
keywords = {(GBML), (LCS), agent agent, algorithms, autonomous brigade, bucket classifier computation, evolutionary genetic genetics-based intelligent learning learning, machine programming, reinforcement system},
month = {7-11 July},
notes = {Distributed on CD-ROM at GECCO-2007 ACM Order No.
910071},
pages = {2729--2736},
publisher = {ACM Press},
publisher_address = {New York, NY, USA},
timestamp = {2008-06-19T17:41:02.000+0200},
title = {Genetically programmed learning classifier system
description and results},
url = {http://doi.acm.org/10.1145/1274000.1274068},
year = 2007
}