A novel estimation of distribution algorithm using graph-based chromosome representation and reinforcement learning

Xianneng Li; Bing Li; Shingo Mabu; Kotaro Hirasawa

doi:10.1109/CEC.2011.5949595

A novel estimation of distribution algorithm using graph-based chromosome representation and reinforcement learning

Xianneng Li^*, Bing Li, Shingo Mabu, Kotaro Hirasawa

^*Corresponding author for this work

Information, Production and Systems Research Center

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

13 Citations (Scopus)

Abstract

This paper proposed a novel EDA, where a directed graph network is used to represent its chromosome. In the proposed algorithm, a probabilistic model is constructed from the promising individuals of the current generation using reinforcement learning, and used to produce the new population. The node connection probability is studied to develop the probabilistic model, therefore pairwise interactions can be demonstrated to identify and recombine building blocks in the proposed algorithm. The proposed algorithm is applied to a problem of agent control, i.e., autonomous robot control. The experimental results show the superiority of the proposed algorithm comparing with the conventional algorithms.

Original language	English
Title of host publication	2011 IEEE Congress of Evolutionary Computation, CEC 2011
Pages	37-44
Number of pages	8
DOIs	https://doi.org/10.1109/CEC.2011.5949595
Publication status	Published - 2011
Event	2011 IEEE Congress of Evolutionary Computation, CEC 2011 - New Orleans, LA Duration: 2011 Jun 5 → 2011 Jun 8

Other

Other	2011 IEEE Congress of Evolutionary Computation, CEC 2011
City	New Orleans, LA
Period	11/6/5 → 11/6/8

ASJC Scopus subject areas

Computational Theory and Mathematics
Theoretical Computer Science

Access to Document

10.1109/CEC.2011.5949595

Cite this

@inproceedings{0753cdbd80984c4e84ad83e371d3769d,

title = "A novel estimation of distribution algorithm using graph-based chromosome representation and reinforcement learning",

abstract = "This paper proposed a novel EDA, where a directed graph network is used to represent its chromosome. In the proposed algorithm, a probabilistic model is constructed from the promising individuals of the current generation using reinforcement learning, and used to produce the new population. The node connection probability is studied to develop the probabilistic model, therefore pairwise interactions can be demonstrated to identify and recombine building blocks in the proposed algorithm. The proposed algorithm is applied to a problem of agent control, i.e., autonomous robot control. The experimental results show the superiority of the proposed algorithm comparing with the conventional algorithms.",

author = "Xianneng Li and Bing Li and Shingo Mabu and Kotaro Hirasawa",

year = "2011",

doi = "10.1109/CEC.2011.5949595",

language = "English",

isbn = "9781424478347",

pages = "37--44",

booktitle = "2011 IEEE Congress of Evolutionary Computation, CEC 2011",

note = "2011 IEEE Congress of Evolutionary Computation, CEC 2011 ; Conference date: 05-06-2011 Through 08-06-2011",

}

TY - GEN

T1 - A novel estimation of distribution algorithm using graph-based chromosome representation and reinforcement learning

AU - Li, Xianneng

AU - Li, Bing

AU - Mabu, Shingo

AU - Hirasawa, Kotaro

PY - 2011

Y1 - 2011

N2 - This paper proposed a novel EDA, where a directed graph network is used to represent its chromosome. In the proposed algorithm, a probabilistic model is constructed from the promising individuals of the current generation using reinforcement learning, and used to produce the new population. The node connection probability is studied to develop the probabilistic model, therefore pairwise interactions can be demonstrated to identify and recombine building blocks in the proposed algorithm. The proposed algorithm is applied to a problem of agent control, i.e., autonomous robot control. The experimental results show the superiority of the proposed algorithm comparing with the conventional algorithms.

AB - This paper proposed a novel EDA, where a directed graph network is used to represent its chromosome. In the proposed algorithm, a probabilistic model is constructed from the promising individuals of the current generation using reinforcement learning, and used to produce the new population. The node connection probability is studied to develop the probabilistic model, therefore pairwise interactions can be demonstrated to identify and recombine building blocks in the proposed algorithm. The proposed algorithm is applied to a problem of agent control, i.e., autonomous robot control. The experimental results show the superiority of the proposed algorithm comparing with the conventional algorithms.

UR - http://www.scopus.com/inward/record.url?scp=80051965781&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80051965781&partnerID=8YFLogxK

U2 - 10.1109/CEC.2011.5949595

DO - 10.1109/CEC.2011.5949595

M3 - Conference contribution

AN - SCOPUS:80051965781

SN - 9781424478347

SP - 37

EP - 44

BT - 2011 IEEE Congress of Evolutionary Computation, CEC 2011

T2 - 2011 IEEE Congress of Evolutionary Computation, CEC 2011

Y2 - 5 June 2011 through 8 June 2011

ER -

A novel estimation of distribution algorithm using graph-based chromosome representation and reinforcement learning

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this