Genetic network programming - application to intelligent agents

H. Katagiri, K. Hirasawa, Takayuki Furuzuki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

72 Citations (Scopus)

Abstract

Recently many studies have been made on automatic design of the complex systems by using the evolutionary optimization techniques such as Genetic Algorithms (GA), Evolution Strategy (ES), Evolutionary Programming (EP) and Genetic Programming (GP). It is generally recognized that these techniques are very useful for optimizing fairly complex systems such as generation of intelligent behavior sequences of robots. In this paper, a new method named Genetic network Programming (GNP) is proposed in order to acquire these behavior sequences efficiently. GNP is composed of plural nodes for agents to execute simple judgment/processing and they are connected with each other to form a network structure. Agents behave according to the contents of the nodes and their connections in GNP. In order to obtain better structure, GNP changes itself by using evolutionary optimization techniques.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Systems, Man and Cybernetics
PublisherIEEE
Pages3829-3834
Number of pages6
Volume5
Publication statusPublished - 2000
Externally publishedYes
Event2000 IEEE International Conference on Systems, Man and Cybernetics - Nashville, TN, USA
Duration: 2000 Oct 82000 Oct 11

Other

Other2000 IEEE International Conference on Systems, Man and Cybernetics
CityNashville, TN, USA
Period00/10/800/10/11

Fingerprint

Intelligent agents
Large scale systems
Genetic programming
Evolutionary algorithms
Genetic algorithms
Robots
Processing

ASJC Scopus subject areas

  • Hardware and Architecture
  • Control and Systems Engineering

Cite this

Katagiri, H., Hirasawa, K., & Furuzuki, T. (2000). Genetic network programming - application to intelligent agents. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (Vol. 5, pp. 3829-3834). IEEE.

Genetic network programming - application to intelligent agents. / Katagiri, H.; Hirasawa, K.; Furuzuki, Takayuki.

Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 5 IEEE, 2000. p. 3829-3834.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Katagiri, H, Hirasawa, K & Furuzuki, T 2000, Genetic network programming - application to intelligent agents. in Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. vol. 5, IEEE, pp. 3829-3834, 2000 IEEE International Conference on Systems, Man and Cybernetics, Nashville, TN, USA, 00/10/8.
Katagiri H, Hirasawa K, Furuzuki T. Genetic network programming - application to intelligent agents. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 5. IEEE. 2000. p. 3829-3834
Katagiri, H. ; Hirasawa, K. ; Furuzuki, Takayuki. / Genetic network programming - application to intelligent agents. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 5 IEEE, 2000. pp. 3829-3834
@inproceedings{6b70dac2763d496d96d635e6ddabe075,
title = "Genetic network programming - application to intelligent agents",
abstract = "Recently many studies have been made on automatic design of the complex systems by using the evolutionary optimization techniques such as Genetic Algorithms (GA), Evolution Strategy (ES), Evolutionary Programming (EP) and Genetic Programming (GP). It is generally recognized that these techniques are very useful for optimizing fairly complex systems such as generation of intelligent behavior sequences of robots. In this paper, a new method named Genetic network Programming (GNP) is proposed in order to acquire these behavior sequences efficiently. GNP is composed of plural nodes for agents to execute simple judgment/processing and they are connected with each other to form a network structure. Agents behave according to the contents of the nodes and their connections in GNP. In order to obtain better structure, GNP changes itself by using evolutionary optimization techniques.",
author = "H. Katagiri and K. Hirasawa and Takayuki Furuzuki",
year = "2000",
language = "English",
volume = "5",
pages = "3829--3834",
booktitle = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",
publisher = "IEEE",

}

TY - GEN

T1 - Genetic network programming - application to intelligent agents

AU - Katagiri, H.

AU - Hirasawa, K.

AU - Furuzuki, Takayuki

PY - 2000

Y1 - 2000

N2 - Recently many studies have been made on automatic design of the complex systems by using the evolutionary optimization techniques such as Genetic Algorithms (GA), Evolution Strategy (ES), Evolutionary Programming (EP) and Genetic Programming (GP). It is generally recognized that these techniques are very useful for optimizing fairly complex systems such as generation of intelligent behavior sequences of robots. In this paper, a new method named Genetic network Programming (GNP) is proposed in order to acquire these behavior sequences efficiently. GNP is composed of plural nodes for agents to execute simple judgment/processing and they are connected with each other to form a network structure. Agents behave according to the contents of the nodes and their connections in GNP. In order to obtain better structure, GNP changes itself by using evolutionary optimization techniques.

AB - Recently many studies have been made on automatic design of the complex systems by using the evolutionary optimization techniques such as Genetic Algorithms (GA), Evolution Strategy (ES), Evolutionary Programming (EP) and Genetic Programming (GP). It is generally recognized that these techniques are very useful for optimizing fairly complex systems such as generation of intelligent behavior sequences of robots. In this paper, a new method named Genetic network Programming (GNP) is proposed in order to acquire these behavior sequences efficiently. GNP is composed of plural nodes for agents to execute simple judgment/processing and they are connected with each other to form a network structure. Agents behave according to the contents of the nodes and their connections in GNP. In order to obtain better structure, GNP changes itself by using evolutionary optimization techniques.

UR - http://www.scopus.com/inward/record.url?scp=0034516030&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034516030&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0034516030

VL - 5

SP - 3829

EP - 3834

BT - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

PB - IEEE

ER -