Genetic Network Programming with reinforcement learning for generating agent behavior in the benchmark problems

Shingo Mabu; Kotaro Hirasawa; Jinglu Hu

Genetic Network Programming with reinforcement learning for generating agent behavior in the benchmark problems

Shingo Mabu^*, Kotaro Hirasawa, Jinglu Hu

^*この研究の対応する著者

大学院情報生産システム研究科

研究成果: Paper › 査読

抄録

A new graph-based evolutionary algorithm named "Genetic Network Programming, GNP" has been proposed. GNP represents its solutions as graph structures which have distinguished expression ability. In this paper, we propose GNP with Reinforcement Learning. Evolutionary algorithm of GNP makes a very compact graph structure and Reinforcement Learning of GNP improves search speed for solutions.

本文言語	English
ページ	605-610
ページ数	6
出版ステータス	Published - 2004
イベント	SICE Annual Conference 2004 - Sapporo, Japan 継続期間: 2004 8月 4 → 2004 8月 6

Conference

Conference	SICE Annual Conference 2004
国/地域	Japan
City	Sapporo
Period	04/8/4 → 04/8/6

ASJC Scopus subject areas

制御およびシステム工学
コンピュータサイエンスの応用
電子工学および電気工学

他のファイルとリンク

引用スタイル

@conference{0ae073cf1a344bc8a26566130e82fb5b,

title = "Genetic Network Programming with reinforcement learning for generating agent behavior in the benchmark problems",

abstract = "A new graph-based evolutionary algorithm named {"}Genetic Network Programming, GNP{"} has been proposed. GNP represents its solutions as graph structures which have distinguished expression ability. In this paper, we propose GNP with Reinforcement Learning. Evolutionary algorithm of GNP makes a very compact graph structure and Reinforcement Learning of GNP improves search speed for solutions.",

keywords = "Agent, Genetic Programming, Graph structure, Reinforcement Learning",

author = "Shingo Mabu and Kotaro Hirasawa and Jinglu Hu",

year = "2004",

language = "English",

pages = "605--610",

note = "SICE Annual Conference 2004 ; Conference date: 04-08-2004 Through 06-08-2004",

}

TY - CONF

T1 - Genetic Network Programming with reinforcement learning for generating agent behavior in the benchmark problems

AU - Mabu, Shingo

AU - Hirasawa, Kotaro

AU - Hu, Jinglu

PY - 2004

Y1 - 2004

N2 - A new graph-based evolutionary algorithm named "Genetic Network Programming, GNP" has been proposed. GNP represents its solutions as graph structures which have distinguished expression ability. In this paper, we propose GNP with Reinforcement Learning. Evolutionary algorithm of GNP makes a very compact graph structure and Reinforcement Learning of GNP improves search speed for solutions.

AB - A new graph-based evolutionary algorithm named "Genetic Network Programming, GNP" has been proposed. GNP represents its solutions as graph structures which have distinguished expression ability. In this paper, we propose GNP with Reinforcement Learning. Evolutionary algorithm of GNP makes a very compact graph structure and Reinforcement Learning of GNP improves search speed for solutions.

KW - Agent

KW - Genetic Programming

KW - Graph structure

KW - Reinforcement Learning

UR - http://www.scopus.com/inward/record.url?scp=12744274815&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=12744274815&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:12744274815

SP - 605

EP - 610

T2 - SICE Annual Conference 2004

Y2 - 4 August 2004 through 6 August 2004

ER -

Genetic Network Programming with reinforcement learning for generating agent behavior in the benchmark problems

抄録

Conference

ASJC Scopus subject areas

他のファイルとリンク

フィンガープリント

引用スタイル