An extension of genetic network programming with reinforcement learning using actor-critic

Hiroyuki Hatakeyama; Shingo Mabu; Kotaro Hirasawa; Jinglu Hu

An extension of genetic network programming with reinforcement learning using actor-critic

Hiroyuki Hatakeyama^*, Shingo Mabu, Kotaro Hirasawa, Jinglu Hu

^*Corresponding author for this work

Graduate School of Information, Production and Systems

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

1 Citation (Scopus)

Abstract

A new graph-based evolutionary algorithm named "Genetic Network Programming, GNP" has been already proposed. GNP represents its solutions as graph structures, which can improve the expression ability and performance. In addition, GNP with Reinforcement Learning (GNP-RL) was proposed a few years ago. Since GNP-RL can do reinforcement learning during task execution in addition to evolution after task execution, it can search for solutions efficiently. In this paper, GNP with Actor-Critic (GNP-AC) which is a new type of GNP-RL is proposed. Originally, GNP deals with discrete information, but GNP-AC aims to deal with continuous information. The proposed method is applied to the controller of the Khepera simulator and its performance is evaluated.

Original language	English
Title of host publication	2006 IEEE Congress on Evolutionary Computation, CEC 2006
Pages	1537-1543
Number of pages	7
Publication status	Published - 2006 Dec 1
Event	2006 IEEE Congress on Evolutionary Computation, CEC 2006 - Vancouver, BC, Canada Duration: 2006 Jul 16 → 2006 Jul 21

Publication series

Name	2006 IEEE Congress on Evolutionary Computation, CEC 2006

Conference

Conference	2006 IEEE Congress on Evolutionary Computation, CEC 2006
Country/Territory	Canada
City	Vancouver, BC
Period	06/7/16 → 06/7/21

ASJC Scopus subject areas

Artificial Intelligence
Software
Theoretical Computer Science

Cite this

An extension of genetic network programming with reinforcement learning using actor-critic. / Hatakeyama, Hiroyuki; Mabu, Shingo; Hirasawa, Kotaro et al.

2006 IEEE Congress on Evolutionary Computation, CEC 2006. 2006. p. 1537-1543 1688491 (2006 IEEE Congress on Evolutionary Computation, CEC 2006).

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

Hatakeyama, H, Mabu, S, Hirasawa, K & Hu, J 2006, An extension of genetic network programming with reinforcement learning using actor-critic. in 2006 IEEE Congress on Evolutionary Computation, CEC 2006., 1688491, 2006 IEEE Congress on Evolutionary Computation, CEC 2006, pp. 1537-1543, 2006 IEEE Congress on Evolutionary Computation, CEC 2006, Vancouver, BC, Canada, 06/7/16.

@inproceedings{6688f17498404bfeb51d839918834f0a,

title = "An extension of genetic network programming with reinforcement learning using actor-critic",

abstract = "A new graph-based evolutionary algorithm named {"}Genetic Network Programming, GNP{"} has been already proposed. GNP represents its solutions as graph structures, which can improve the expression ability and performance. In addition, GNP with Reinforcement Learning (GNP-RL) was proposed a few years ago. Since GNP-RL can do reinforcement learning during task execution in addition to evolution after task execution, it can search for solutions efficiently. In this paper, GNP with Actor-Critic (GNP-AC) which is a new type of GNP-RL is proposed. Originally, GNP deals with discrete information, but GNP-AC aims to deal with continuous information. The proposed method is applied to the controller of the Khepera simulator and its performance is evaluated.",

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

year = "2006",

month = dec,

day = "1",

language = "English",

isbn = "0780394879",

series = "2006 IEEE Congress on Evolutionary Computation, CEC 2006",

pages = "1537--1543",

booktitle = "2006 IEEE Congress on Evolutionary Computation, CEC 2006",

note = "2006 IEEE Congress on Evolutionary Computation, CEC 2006 ; Conference date: 16-07-2006 Through 21-07-2006",

}

TY - GEN

T1 - An extension of genetic network programming with reinforcement learning using actor-critic

AU - Hatakeyama, Hiroyuki

AU - Mabu, Shingo

AU - Hirasawa, Kotaro

AU - Hu, Jinglu

PY - 2006/12/1

Y1 - 2006/12/1

N2 - A new graph-based evolutionary algorithm named "Genetic Network Programming, GNP" has been already proposed. GNP represents its solutions as graph structures, which can improve the expression ability and performance. In addition, GNP with Reinforcement Learning (GNP-RL) was proposed a few years ago. Since GNP-RL can do reinforcement learning during task execution in addition to evolution after task execution, it can search for solutions efficiently. In this paper, GNP with Actor-Critic (GNP-AC) which is a new type of GNP-RL is proposed. Originally, GNP deals with discrete information, but GNP-AC aims to deal with continuous information. The proposed method is applied to the controller of the Khepera simulator and its performance is evaluated.

AB - A new graph-based evolutionary algorithm named "Genetic Network Programming, GNP" has been already proposed. GNP represents its solutions as graph structures, which can improve the expression ability and performance. In addition, GNP with Reinforcement Learning (GNP-RL) was proposed a few years ago. Since GNP-RL can do reinforcement learning during task execution in addition to evolution after task execution, it can search for solutions efficiently. In this paper, GNP with Actor-Critic (GNP-AC) which is a new type of GNP-RL is proposed. Originally, GNP deals with discrete information, but GNP-AC aims to deal with continuous information. The proposed method is applied to the controller of the Khepera simulator and its performance is evaluated.

UR - http://www.scopus.com/inward/record.url?scp=34547365679&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547365679&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:34547365679

SN - 0780394879

SN - 9780780394872

T3 - 2006 IEEE Congress on Evolutionary Computation, CEC 2006

SP - 1537

EP - 1543

BT - 2006 IEEE Congress on Evolutionary Computation, CEC 2006

T2 - 2006 IEEE Congress on Evolutionary Computation, CEC 2006

Y2 - 16 July 2006 through 21 July 2006

ER -

An extension of genetic network programming with reinforcement learning using actor-critic

Abstract

Publication series

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this