Combining genetic algorithm and swarm intelligence for task allocation in a real time strategy game

Detalhes bibliográficos
Autor(a) principal: Tavares, Anderson R.
Data de Publicação: 2017
Outros Autores: Zuin, Gianlucca Lodron, Azpúrua, Héctor, Chaimowicz, Luiz
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Journal on Interactive Systems
Texto Completo: https://sol.sbc.org.br/journals/index.php/jis/article/view/671
Resumo: Real time strategy games are complex scenarios where multiple agents must be coordinated in a dynamic, partially observable environment. In this work, we model coordination as a task allocation problem, in which specific tasks must be properly assigned to agents. We employ a task allocation algorithm based on swarm intelligence and adjust its parameters using a genetic algorithm. A fitness estimation method is employed to accelerate execution of the genetic algorithm. To evaluate this approach, we implement this coordination mechanism in the AI of a popular video game: StarCraft: BroodWar. Experiment results show that the genetic algorithm successfully adjusts task allocation parameters. Besides, we assess the trade-off between solution quality and execution time of the genetic algorithm with fitness estimation.
id SBC-3_6a925dfa1403c3532c80dd1350166d3e
oai_identifier_str oai:ojs2.sol.sbc.org.br:article/671
network_acronym_str SBC-3
network_name_str Journal on Interactive Systems
repository_id_str
spelling Combining genetic algorithm and swarm intelligence for task allocation in a real time strategy gameReal time strategy games are complex scenarios where multiple agents must be coordinated in a dynamic, partially observable environment. In this work, we model coordination as a task allocation problem, in which specific tasks must be properly assigned to agents. We employ a task allocation algorithm based on swarm intelligence and adjust its parameters using a genetic algorithm. A fitness estimation method is employed to accelerate execution of the genetic algorithm. To evaluate this approach, we implement this coordination mechanism in the AI of a popular video game: StarCraft: BroodWar. Experiment results show that the genetic algorithm successfully adjusts task allocation parameters. Besides, we assess the trade-off between solution quality and execution time of the genetic algorithm with fitness estimation.Nenhum resumo disponívelBrazilian Computer Society2017-09-14info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://sol.sbc.org.br/journals/index.php/jis/article/view/67110.5753/jis.2017.671Journal of Interactive Systems; v. 8 n. 1 (2017)Journal on Interactive Systems; Vol. 8 No. 1 (2017)2763-7719reponame:Journal on Interactive Systemsinstname:Sociedade Brasileira de Computação (SBC)instacron:SBCenghttps://sol.sbc.org.br/journals/index.php/jis/article/view/671/666Tavares, Anderson R.Zuin, Gianlucca LodronAzpúrua, HéctorChaimowicz, Luizinfo:eu-repo/semantics/openAccess2020-09-05T16:09:09Zoai:ojs2.sol.sbc.org.br:article/671Revistahttps://sol.sbc.org.br/journals/index.php/jis/ONGhttps://sol.sbc.org.br/journals/index.php/jis/oaijis@sbc.org.br2763-77192763-7719opendoar:2020-09-05T16:09:09Journal on Interactive Systems - Sociedade Brasileira de Computação (SBC)false
dc.title.none.fl_str_mv Combining genetic algorithm and swarm intelligence for task allocation in a real time strategy game
title Combining genetic algorithm and swarm intelligence for task allocation in a real time strategy game
spellingShingle Combining genetic algorithm and swarm intelligence for task allocation in a real time strategy game
Tavares, Anderson R.
title_short Combining genetic algorithm and swarm intelligence for task allocation in a real time strategy game
title_full Combining genetic algorithm and swarm intelligence for task allocation in a real time strategy game
title_fullStr Combining genetic algorithm and swarm intelligence for task allocation in a real time strategy game
title_full_unstemmed Combining genetic algorithm and swarm intelligence for task allocation in a real time strategy game
title_sort Combining genetic algorithm and swarm intelligence for task allocation in a real time strategy game
author Tavares, Anderson R.
author_facet Tavares, Anderson R.
Zuin, Gianlucca Lodron
Azpúrua, Héctor
Chaimowicz, Luiz
author_role author
author2 Zuin, Gianlucca Lodron
Azpúrua, Héctor
Chaimowicz, Luiz
author2_role author
author
author
dc.contributor.author.fl_str_mv Tavares, Anderson R.
Zuin, Gianlucca Lodron
Azpúrua, Héctor
Chaimowicz, Luiz
description Real time strategy games are complex scenarios where multiple agents must be coordinated in a dynamic, partially observable environment. In this work, we model coordination as a task allocation problem, in which specific tasks must be properly assigned to agents. We employ a task allocation algorithm based on swarm intelligence and adjust its parameters using a genetic algorithm. A fitness estimation method is employed to accelerate execution of the genetic algorithm. To evaluate this approach, we implement this coordination mechanism in the AI of a popular video game: StarCraft: BroodWar. Experiment results show that the genetic algorithm successfully adjusts task allocation parameters. Besides, we assess the trade-off between solution quality and execution time of the genetic algorithm with fitness estimation.
publishDate 2017
dc.date.none.fl_str_mv 2017-09-14
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://sol.sbc.org.br/journals/index.php/jis/article/view/671
10.5753/jis.2017.671
url https://sol.sbc.org.br/journals/index.php/jis/article/view/671
identifier_str_mv 10.5753/jis.2017.671
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv https://sol.sbc.org.br/journals/index.php/jis/article/view/671/666
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Brazilian Computer Society
publisher.none.fl_str_mv Brazilian Computer Society
dc.source.none.fl_str_mv Journal of Interactive Systems; v. 8 n. 1 (2017)
Journal on Interactive Systems; Vol. 8 No. 1 (2017)
2763-7719
reponame:Journal on Interactive Systems
instname:Sociedade Brasileira de Computação (SBC)
instacron:SBC
instname_str Sociedade Brasileira de Computação (SBC)
instacron_str SBC
institution SBC
reponame_str Journal on Interactive Systems
collection Journal on Interactive Systems
repository.name.fl_str_mv Journal on Interactive Systems - Sociedade Brasileira de Computação (SBC)
repository.mail.fl_str_mv jis@sbc.org.br
_version_ 1796797410994814976