A learning classifier system based on genetic network programming

Xianneng Li; Kotaro Hirasawa

doi:10.1109/SMC.2013.229

A learning classifier system based on genetic network programming

Xianneng Li, Kotaro Hirasawa

Information, Production and Systems Research Center

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

8 Citations (Scopus)

Abstract

Recent advances in Learning Classifier Systems (LCSs) have shown their sequential decision-making ability with a generalization property. In this paper, a novel LCS named eXtended rule-based Genetic Network Programming (XrGNP) is proposed. Different from most of the current LCSs, the rules are represented and discovered through a graph-based evolutionary algorithm GNP, which consequently has the distinct expression ability to model and evolve the decision-making rules. XrGNP is described in details in which its unique features are explicitly mapped. Experiments on benchmark and real-world multi-step problems demonstrate the effectiveness of XrGNP.

Original language	English
Title of host publication	Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013
Pages	1323-1328
Number of pages	6
DOIs	https://doi.org/10.1109/SMC.2013.229
Publication status	Published - 2013
Event	2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013 - Manchester, United Kingdom Duration: 2013 Oct 13 → 2013 Oct 16

Other

Other	2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013
Country/Territory	United Kingdom
City	Manchester
Period	13/10/13 → 13/10/16

Keywords

Fitness sharing
Genetic network programming
Learning classifier systems
Niching
Reinforcement learning

ASJC Scopus subject areas

Human-Computer Interaction

Access to Document

10.1109/SMC.2013.229

Cite this

@inproceedings{3d58c08bfd904b289d984e3230de3b3e,

title = "A learning classifier system based on genetic network programming",

abstract = "Recent advances in Learning Classifier Systems (LCSs) have shown their sequential decision-making ability with a generalization property. In this paper, a novel LCS named eXtended rule-based Genetic Network Programming (XrGNP) is proposed. Different from most of the current LCSs, the rules are represented and discovered through a graph-based evolutionary algorithm GNP, which consequently has the distinct expression ability to model and evolve the decision-making rules. XrGNP is described in details in which its unique features are explicitly mapped. Experiments on benchmark and real-world multi-step problems demonstrate the effectiveness of XrGNP.",

keywords = "Fitness sharing, Genetic network programming, Learning classifier systems, Niching, Reinforcement learning",

author = "Xianneng Li and Kotaro Hirasawa",

year = "2013",

doi = "10.1109/SMC.2013.229",

language = "English",

isbn = "9780769551548",

pages = "1323--1328",

booktitle = "Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013",

note = "2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013 ; Conference date: 13-10-2013 Through 16-10-2013",

}

TY - GEN

T1 - A learning classifier system based on genetic network programming

AU - Li, Xianneng

AU - Hirasawa, Kotaro

PY - 2013

Y1 - 2013

N2 - Recent advances in Learning Classifier Systems (LCSs) have shown their sequential decision-making ability with a generalization property. In this paper, a novel LCS named eXtended rule-based Genetic Network Programming (XrGNP) is proposed. Different from most of the current LCSs, the rules are represented and discovered through a graph-based evolutionary algorithm GNP, which consequently has the distinct expression ability to model and evolve the decision-making rules. XrGNP is described in details in which its unique features are explicitly mapped. Experiments on benchmark and real-world multi-step problems demonstrate the effectiveness of XrGNP.

AB - Recent advances in Learning Classifier Systems (LCSs) have shown their sequential decision-making ability with a generalization property. In this paper, a novel LCS named eXtended rule-based Genetic Network Programming (XrGNP) is proposed. Different from most of the current LCSs, the rules are represented and discovered through a graph-based evolutionary algorithm GNP, which consequently has the distinct expression ability to model and evolve the decision-making rules. XrGNP is described in details in which its unique features are explicitly mapped. Experiments on benchmark and real-world multi-step problems demonstrate the effectiveness of XrGNP.

KW - Fitness sharing

KW - Genetic network programming

KW - Learning classifier systems

KW - Niching

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=84893547065&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893547065&partnerID=8YFLogxK

U2 - 10.1109/SMC.2013.229

DO - 10.1109/SMC.2013.229

M3 - Conference contribution

AN - SCOPUS:84893547065

SN - 9780769551548

SP - 1323

EP - 1328

BT - Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013

T2 - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013

Y2 - 13 October 2013 through 16 October 2013

ER -

A learning classifier system based on genetic network programming

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this