An application of the genetic programming technique to strategy development

Koun Tem Sun, Yi Chun Lin, Cheng Yen Wu, Yueh-Min Huang

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

In this paper, we will apply genetic programming (GP) and co-evolution techniques to develop two strategies: the ghost (attacker) and players (survivors) in the Traffic Light Game (a popular game among children). These two strategies compete against each other. By applying the co-evolution technique alongside GP, each strategy is used as an "imaginary enemy" from which evolves (is trained in) another strategy. Based on this co-evolutionary process, these final strategies develop: the ghost can effectively capture the players, but the players can also escape from the ghost, rescue partners, and detour around obstacles. The development of these strategies has achieved phenomenal success. The results encourage us to develop more complex strategies or cooperative models such as human learning models, cooperative robotic models, and self-learning of virtual agents.

Original languageEnglish
Pages (from-to)5157-5161
Number of pages5
JournalExpert Systems With Applications
Volume36
Issue number3 PART 1
DOIs
Publication statusPublished - 2009 Jan 1

Fingerprint

Genetic programming
Telecommunication traffic
Robotics

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

Cite this

Sun, Koun Tem ; Lin, Yi Chun ; Wu, Cheng Yen ; Huang, Yueh-Min. / An application of the genetic programming technique to strategy development. In: Expert Systems With Applications. 2009 ; Vol. 36, No. 3 PART 1. pp. 5157-5161.
@article{aa6de25835c44b109ca89ebd1e7a743f,
title = "An application of the genetic programming technique to strategy development",
abstract = "In this paper, we will apply genetic programming (GP) and co-evolution techniques to develop two strategies: the ghost (attacker) and players (survivors) in the Traffic Light Game (a popular game among children). These two strategies compete against each other. By applying the co-evolution technique alongside GP, each strategy is used as an {"}imaginary enemy{"} from which evolves (is trained in) another strategy. Based on this co-evolutionary process, these final strategies develop: the ghost can effectively capture the players, but the players can also escape from the ghost, rescue partners, and detour around obstacles. The development of these strategies has achieved phenomenal success. The results encourage us to develop more complex strategies or cooperative models such as human learning models, cooperative robotic models, and self-learning of virtual agents.",
author = "Sun, {Koun Tem} and Lin, {Yi Chun} and Wu, {Cheng Yen} and Yueh-Min Huang",
year = "2009",
month = "1",
day = "1",
doi = "10.1016/j.eswa.2008.06.066",
language = "English",
volume = "36",
pages = "5157--5161",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "3 PART 1",

}

An application of the genetic programming technique to strategy development. / Sun, Koun Tem; Lin, Yi Chun; Wu, Cheng Yen; Huang, Yueh-Min.

In: Expert Systems With Applications, Vol. 36, No. 3 PART 1, 01.01.2009, p. 5157-5161.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An application of the genetic programming technique to strategy development

AU - Sun, Koun Tem

AU - Lin, Yi Chun

AU - Wu, Cheng Yen

AU - Huang, Yueh-Min

PY - 2009/1/1

Y1 - 2009/1/1

N2 - In this paper, we will apply genetic programming (GP) and co-evolution techniques to develop two strategies: the ghost (attacker) and players (survivors) in the Traffic Light Game (a popular game among children). These two strategies compete against each other. By applying the co-evolution technique alongside GP, each strategy is used as an "imaginary enemy" from which evolves (is trained in) another strategy. Based on this co-evolutionary process, these final strategies develop: the ghost can effectively capture the players, but the players can also escape from the ghost, rescue partners, and detour around obstacles. The development of these strategies has achieved phenomenal success. The results encourage us to develop more complex strategies or cooperative models such as human learning models, cooperative robotic models, and self-learning of virtual agents.

AB - In this paper, we will apply genetic programming (GP) and co-evolution techniques to develop two strategies: the ghost (attacker) and players (survivors) in the Traffic Light Game (a popular game among children). These two strategies compete against each other. By applying the co-evolution technique alongside GP, each strategy is used as an "imaginary enemy" from which evolves (is trained in) another strategy. Based on this co-evolutionary process, these final strategies develop: the ghost can effectively capture the players, but the players can also escape from the ghost, rescue partners, and detour around obstacles. The development of these strategies has achieved phenomenal success. The results encourage us to develop more complex strategies or cooperative models such as human learning models, cooperative robotic models, and self-learning of virtual agents.

UR - http://www.scopus.com/inward/record.url?scp=58349114032&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=58349114032&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2008.06.066

DO - 10.1016/j.eswa.2008.06.066

M3 - Article

VL - 36

SP - 5157

EP - 5161

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 3 PART 1

ER -