Elevator group supervisory control system using genetic network programming with reinforcement learning

Jin Zhou, Toru Eguchi, Kotaro Hirasawa, Takayuki Furuzuki, Sandor Markon

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

5 Citations (Scopus)

Abstract

Since Genetic Network Programming (GNP) has been proposed as a new method of evolutionary computation, many studies have been done on its applications which cover not only virtual world problems but also real world systems like Elevator Group Supervisory Control System (EGSCS) which is a very large scale stochastic dynamic optimization problem. From those researches, most of the significant features of GNP have been verified comparing to Genetic Algorithm (GA) and Genetic Programming (GP). Especially, the improvement of the performances on EGSCS using GNP showed an interesting and promising prospect in this field. On the other hand, some studies based on GNP with Reinforcement Learning (RL) revealed a better performance over conventional GNP on some problems such as tile-world models. As a basic study, Reinforcement Learning is introduced in this paper expecting to enhance EGSCS controller using GNP.

Original languageEnglish
Title of host publication2005 IEEE Congress on Evolutionary Computation, IEEE CEC 2005. Proceedings
Pages336-342
Number of pages7
Volume1
Publication statusPublished - 2005
Event2005 IEEE Congress on Evolutionary Computation, IEEE CEC 2005 - Edinburgh, Scotland
Duration: 2005 Sep 22005 Sep 5

Other

Other2005 IEEE Congress on Evolutionary Computation, IEEE CEC 2005
CityEdinburgh, Scotland
Period05/9/205/9/5

Fingerprint

Elevators
Reinforcement learning
Control systems
Genetic programming
Tile
Evolutionary algorithms
Genetic algorithms
Controllers

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Zhou, J., Eguchi, T., Hirasawa, K., Furuzuki, T., & Markon, S. (2005). Elevator group supervisory control system using genetic network programming with reinforcement learning. In 2005 IEEE Congress on Evolutionary Computation, IEEE CEC 2005. Proceedings (Vol. 1, pp. 336-342)

Elevator group supervisory control system using genetic network programming with reinforcement learning. / Zhou, Jin; Eguchi, Toru; Hirasawa, Kotaro; Furuzuki, Takayuki; Markon, Sandor.

2005 IEEE Congress on Evolutionary Computation, IEEE CEC 2005. Proceedings. Vol. 1 2005. p. 336-342.

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

Zhou, J, Eguchi, T, Hirasawa, K, Furuzuki, T & Markon, S 2005, Elevator group supervisory control system using genetic network programming with reinforcement learning. in 2005 IEEE Congress on Evolutionary Computation, IEEE CEC 2005. Proceedings. vol. 1, pp. 336-342, 2005 IEEE Congress on Evolutionary Computation, IEEE CEC 2005, Edinburgh, Scotland, 05/9/2.
Zhou J, Eguchi T, Hirasawa K, Furuzuki T, Markon S. Elevator group supervisory control system using genetic network programming with reinforcement learning. In 2005 IEEE Congress on Evolutionary Computation, IEEE CEC 2005. Proceedings. Vol. 1. 2005. p. 336-342
Zhou, Jin ; Eguchi, Toru ; Hirasawa, Kotaro ; Furuzuki, Takayuki ; Markon, Sandor. / Elevator group supervisory control system using genetic network programming with reinforcement learning. 2005 IEEE Congress on Evolutionary Computation, IEEE CEC 2005. Proceedings. Vol. 1 2005. pp. 336-342
@inproceedings{3466fe44f3a747ac88af568803908398,
title = "Elevator group supervisory control system using genetic network programming with reinforcement learning",
abstract = "Since Genetic Network Programming (GNP) has been proposed as a new method of evolutionary computation, many studies have been done on its applications which cover not only virtual world problems but also real world systems like Elevator Group Supervisory Control System (EGSCS) which is a very large scale stochastic dynamic optimization problem. From those researches, most of the significant features of GNP have been verified comparing to Genetic Algorithm (GA) and Genetic Programming (GP). Especially, the improvement of the performances on EGSCS using GNP showed an interesting and promising prospect in this field. On the other hand, some studies based on GNP with Reinforcement Learning (RL) revealed a better performance over conventional GNP on some problems such as tile-world models. As a basic study, Reinforcement Learning is introduced in this paper expecting to enhance EGSCS controller using GNP.",
author = "Jin Zhou and Toru Eguchi and Kotaro Hirasawa and Takayuki Furuzuki and Sandor Markon",
year = "2005",
language = "English",
isbn = "0780393635",
volume = "1",
pages = "336--342",
booktitle = "2005 IEEE Congress on Evolutionary Computation, IEEE CEC 2005. Proceedings",

}

TY - GEN

T1 - Elevator group supervisory control system using genetic network programming with reinforcement learning

AU - Zhou, Jin

AU - Eguchi, Toru

AU - Hirasawa, Kotaro

AU - Furuzuki, Takayuki

AU - Markon, Sandor

PY - 2005

Y1 - 2005

N2 - Since Genetic Network Programming (GNP) has been proposed as a new method of evolutionary computation, many studies have been done on its applications which cover not only virtual world problems but also real world systems like Elevator Group Supervisory Control System (EGSCS) which is a very large scale stochastic dynamic optimization problem. From those researches, most of the significant features of GNP have been verified comparing to Genetic Algorithm (GA) and Genetic Programming (GP). Especially, the improvement of the performances on EGSCS using GNP showed an interesting and promising prospect in this field. On the other hand, some studies based on GNP with Reinforcement Learning (RL) revealed a better performance over conventional GNP on some problems such as tile-world models. As a basic study, Reinforcement Learning is introduced in this paper expecting to enhance EGSCS controller using GNP.

AB - Since Genetic Network Programming (GNP) has been proposed as a new method of evolutionary computation, many studies have been done on its applications which cover not only virtual world problems but also real world systems like Elevator Group Supervisory Control System (EGSCS) which is a very large scale stochastic dynamic optimization problem. From those researches, most of the significant features of GNP have been verified comparing to Genetic Algorithm (GA) and Genetic Programming (GP). Especially, the improvement of the performances on EGSCS using GNP showed an interesting and promising prospect in this field. On the other hand, some studies based on GNP with Reinforcement Learning (RL) revealed a better performance over conventional GNP on some problems such as tile-world models. As a basic study, Reinforcement Learning is introduced in this paper expecting to enhance EGSCS controller using GNP.

UR - http://www.scopus.com/inward/record.url?scp=27144448002&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27144448002&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:27144448002

SN - 0780393635

VL - 1

SP - 336

EP - 342

BT - 2005 IEEE Congress on Evolutionary Computation, IEEE CEC 2005. Proceedings

ER -