Evolving reactive NPCs for the real-time simulation game

Jin Hyuk Hong, Sung Bae Cho

Research output: Contribution to conferencePaper

6 Citations (Scopus)

Abstract

AI in computer games has been highlighted in recent, but manual works for designing the AI cost a great deal. An evolutionary algorithm has developed strategies without using features that are based on the developer. Since the real-time reactive selection of behaviors for NPCs is required for better playing, a reactive behavior system consisting neural networks is presented. Using only the raw information on games, the evolutionary algorithm optimizes the reactive behavior system based on a co-evolutionary method. For demonstration of the proposed method, we have developed a real-time simulation game called 'Build & Build'. As the results, we have obtained emergent and interesting behaviors that are adaptive to the environment, and confirmed the applicability of evolutionary approach to designing NPCs' behaviors without relying on human expertise.

Original languageEnglish
Pages86-93
Number of pages8
Publication statusPublished - 2005 Dec 1
Event2005 IEEE Symposium on Computational Intelligence and Games, CIG'05 - Colchester, Essex, United Kingdom
Duration: 2005 Apr 42005 Apr 6

Other

Other2005 IEEE Symposium on Computational Intelligence and Games, CIG'05
CountryUnited Kingdom
CityColchester, Essex
Period05/4/405/4/6

Fingerprint

Evolutionary algorithms
Computer games
Demonstrations
Neural networks
Costs

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Human-Computer Interaction
  • Software

Cite this

Hong, J. H., & Cho, S. B. (2005). Evolving reactive NPCs for the real-time simulation game. 86-93. Paper presented at 2005 IEEE Symposium on Computational Intelligence and Games, CIG'05, Colchester, Essex, United Kingdom.
Hong, Jin Hyuk ; Cho, Sung Bae. / Evolving reactive NPCs for the real-time simulation game. Paper presented at 2005 IEEE Symposium on Computational Intelligence and Games, CIG'05, Colchester, Essex, United Kingdom.8 p.
@conference{bd9321900d7344cfb0f7713420d8b840,
title = "Evolving reactive NPCs for the real-time simulation game",
abstract = "AI in computer games has been highlighted in recent, but manual works for designing the AI cost a great deal. An evolutionary algorithm has developed strategies without using features that are based on the developer. Since the real-time reactive selection of behaviors for NPCs is required for better playing, a reactive behavior system consisting neural networks is presented. Using only the raw information on games, the evolutionary algorithm optimizes the reactive behavior system based on a co-evolutionary method. For demonstration of the proposed method, we have developed a real-time simulation game called 'Build & Build'. As the results, we have obtained emergent and interesting behaviors that are adaptive to the environment, and confirmed the applicability of evolutionary approach to designing NPCs' behaviors without relying on human expertise.",
author = "Hong, {Jin Hyuk} and Cho, {Sung Bae}",
year = "2005",
month = "12",
day = "1",
language = "English",
pages = "86--93",
note = "2005 IEEE Symposium on Computational Intelligence and Games, CIG'05 ; Conference date: 04-04-2005 Through 06-04-2005",

}

Hong, JH & Cho, SB 2005, 'Evolving reactive NPCs for the real-time simulation game', Paper presented at 2005 IEEE Symposium on Computational Intelligence and Games, CIG'05, Colchester, Essex, United Kingdom, 05/4/4 - 05/4/6 pp. 86-93.

Evolving reactive NPCs for the real-time simulation game. / Hong, Jin Hyuk; Cho, Sung Bae.

2005. 86-93 Paper presented at 2005 IEEE Symposium on Computational Intelligence and Games, CIG'05, Colchester, Essex, United Kingdom.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Evolving reactive NPCs for the real-time simulation game

AU - Hong, Jin Hyuk

AU - Cho, Sung Bae

PY - 2005/12/1

Y1 - 2005/12/1

N2 - AI in computer games has been highlighted in recent, but manual works for designing the AI cost a great deal. An evolutionary algorithm has developed strategies without using features that are based on the developer. Since the real-time reactive selection of behaviors for NPCs is required for better playing, a reactive behavior system consisting neural networks is presented. Using only the raw information on games, the evolutionary algorithm optimizes the reactive behavior system based on a co-evolutionary method. For demonstration of the proposed method, we have developed a real-time simulation game called 'Build & Build'. As the results, we have obtained emergent and interesting behaviors that are adaptive to the environment, and confirmed the applicability of evolutionary approach to designing NPCs' behaviors without relying on human expertise.

AB - AI in computer games has been highlighted in recent, but manual works for designing the AI cost a great deal. An evolutionary algorithm has developed strategies without using features that are based on the developer. Since the real-time reactive selection of behaviors for NPCs is required for better playing, a reactive behavior system consisting neural networks is presented. Using only the raw information on games, the evolutionary algorithm optimizes the reactive behavior system based on a co-evolutionary method. For demonstration of the proposed method, we have developed a real-time simulation game called 'Build & Build'. As the results, we have obtained emergent and interesting behaviors that are adaptive to the environment, and confirmed the applicability of evolutionary approach to designing NPCs' behaviors without relying on human expertise.

UR - http://www.scopus.com/inward/record.url?scp=80053646194&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053646194&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:80053646194

SP - 86

EP - 93

ER -

Hong JH, Cho SB. Evolving reactive NPCs for the real-time simulation game. 2005. Paper presented at 2005 IEEE Symposium on Computational Intelligence and Games, CIG'05, Colchester, Essex, United Kingdom.