{"id":{"repo_id":"reykjavik","oai_identifier":"oai:skemman.is:1946/9143"},"canonical_url":"https://search.dev.ndltd.org/etd/reykjavik/oai:skemman.is:1946/9143","repository":{"repo_id":"reykjavik","name":"Reykjavík University","base_url":"https://skemman.is/oai/request"},"display":{"title":"Developing game AI for the real‐time strategy game StarCraft","abstract":"Research into intelligent agents designed to play Real-Time Strategy (RTS) games has been limited compared to the amount of research that has gone into designing agents for playing board games such as chess. This is largely due to the fact that developing an agent for RTS is more complicated. There has been some positive development in the last couple of years though with the introduction of the Brood War API, which allows researchers to hook their AI into the popular RTS game StarCraft. StarCraft provides an interesting platform for AI RTS research due to its large variety of units and balance between playable factions. We designed an AI agent capable of making informed decisions in StarCraft. The agent uses Reinforcement Learning to improve its performance over time. Empirical evaluation of the agent shows this type of an approach to be viable in RTS games.","abstract_html":"Research into intelligent agents designed to play Real-Time Strategy (RTS) games has been limited compared to the amount of research that has gone into designing agents for playing board games such as chess. This is largely due to the fact that developing an agent for RTS is more complicated. There has been some positive development in the last couple of years though with the introduction of the Brood War API, which allows researchers to hook their AI into the popular RTS game StarCraft. StarCraft provides an interesting platform for AI RTS research due to its large variety of units and balance between playable factions. We designed an AI agent capable of making informed decisions in StarCraft. The agent uses Reinforcement Learning to improve its performance over time. Empirical evaluation of the agent shows this type of an approach to be viable in RTS games.","abstract_has_math":false,"creators":["Aleksandar Micić 1986-","Davíð Arnarsson 1988-","Vignir Jónsson 1988-"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Háskólinn í Reykjavík"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2011,"date_issued":"2011-06-09","date_published":"2011-06-09","updated_at":"2026-07-27T20:39:57Z","subjects":["Gervigreind","Forritun","Tölvunarfræði","Artificial intelligence","Programming (Electronic computers)"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1946/9143","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Háskólinn í Reykjavík"]},{"key":"dc:creator","label":"Author","values":["Aleksandar Micić 1986-","Davíð Arnarsson 1988-","Vignir Jónsson 1988-"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2011-06-09T13:57:27Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2011-06-09T13:57:27Z"]},{"key":"dc:date.issued","label":"Date","values":["2011-06-09"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Gervigreind","Forritun","Tölvunarfræði","Artificial intelligence","Programming (Electronic computers)"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1946/9143"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Heildartexti lokaskýrslu. Prentuð útgáfa og öll fylgiskjöl á CD eru varðveitt í bókasafni HR."]},{"key":"dc:description.abstract","label":"Abstract","values":["Research into intelligent agents designed to play Real-Time Strategy (RTS) games has been limited compared to the amount of research that has gone into designing agents for playing board games such as chess. This is largely due to the fact that developing an agent for RTS is more complicated. There has been some positive development in the last couple of years though with the introduction of the Brood War API, which allows researchers to hook their AI into the popular RTS game StarCraft. StarCraft provides an interesting platform for AI RTS research due to its large variety of units and balance between playable factions. We designed an AI agent capable of making informed decisions in StarCraft. The agent uses Reinforcement Learning to improve its performance over time. Empirical evaluation of the agent shows this type of an approach to be viable in RTS games.","Lítið hefur verið um rannsóknir á hönnun gervigreindra forrita sem að spila Rauntíma herkænsku (RTH) leiki í samanburði við það magn rannsókna sem hafa farið fram á hönnun forrita sem að spila borðspil svo sem skák. Þetta er að stórum hluta vegna þess hve flókið það er að hanna gervigreind forrit fyrir þessa rauntíma leiki. Á undanförnum árum hefur þó orðið jákvæð þróun, þökk sé hinum svo kallaða Brood War API, sem að leyfir rannsóknarmönnum að tengja forritin sín við hinn sívinsæla RTH leik StarCraft. StarCraft er góður grunnur fyrir RTH rannsóknir á sviði gervigreindar vegna mikils úrvals peða(e. Units) og jafnvægis milli liða. Við þróuðum gervigreint forrit sem að getur tekið ákvarðanir byggðar á umhverfi sínu í rauntímaherkænskuleikjum. Forritið notar Reinforcement Learning til að betrumbæta hegðun sína eftir því sem að fleiri leikir eru spilaðir. Tilraunir með forritið sýna að sú aðferð er raunhæfur kostur í þróun ervigreindar fyrir RTH leiki."]},{"key":"dc:title","label":"Title","values":["Developing game AI for the real‐time strategy game StarCraft","Þróun gervigreindar fyrir rauntímaherkænskuleikinn StarCraft"]}]}],"canonical_facts":{"dc:contributor":["Háskólinn í Reykjavík"],"dc:creator":["Aleksandar Micić 1986-","Davíð Arnarsson 1988-","Vignir Jónsson 1988-"],"dc:date.accessioned":["2011-06-09T13:57:27Z"],"dc:date.available":["2011-06-09T13:57:27Z"],"dc:date.issued":["2011-06-09"],"dc:description":["Heildartexti lokaskýrslu. Prentuð útgáfa og öll fylgiskjöl á CD eru varðveitt í bókasafni HR."],"dc:description.abstract":["Research into intelligent agents designed to play Real-Time Strategy (RTS) games has been limited compared to the amount of research that has gone into designing agents for playing board games such as chess. This is largely due to the fact that developing an agent for RTS is more complicated. There has been some positive development in the last couple of years though with the introduction of the Brood War API, which allows researchers to hook their AI into the popular RTS game StarCraft. StarCraft provides an interesting platform for AI RTS research due to its large variety of units and balance between playable factions. We designed an AI agent capable of making informed decisions in StarCraft. The agent uses Reinforcement Learning to improve its performance over time. Empirical evaluation of the agent shows this type of an approach to be viable in RTS games.","Lítið hefur verið um rannsóknir á hönnun gervigreindra forrita sem að spila Rauntíma herkænsku (RTH) leiki í samanburði við það magn rannsókna sem hafa farið fram á hönnun forrita sem að spila borðspil svo sem skák. Þetta er að stórum hluta vegna þess hve flókið það er að hanna gervigreind forrit fyrir þessa rauntíma leiki. Á undanförnum árum hefur þó orðið jákvæð þróun, þökk sé hinum svo kallaða Brood War API, sem að leyfir rannsóknarmönnum að tengja forritin sín við hinn sívinsæla RTH leik StarCraft. StarCraft er góður grunnur fyrir RTH rannsóknir á sviði gervigreindar vegna mikils úrvals peða(e. Units) og jafnvægis milli liða. Við þróuðum gervigreint forrit sem að getur tekið ákvarðanir byggðar á umhverfi sínu í rauntímaherkænskuleikjum. Forritið notar Reinforcement Learning til að betrumbæta hegðun sína eftir því sem að fleiri leikir eru spilaðir. Tilraunir með forritið sýna að sú aðferð er raunhæfur kostur í þróun ervigreindar fyrir RTH leiki."],"dc:identifier.uri":["http://hdl.handle.net/1946/9143"],"dc:language.iso":["en"],"dc:subject":["Gervigreind","Forritun","Tölvunarfræði","Artificial intelligence","Programming (Electronic computers)"],"dc:title":["Developing game AI for the real‐time strategy game StarCraft","Þróun gervigreindar fyrir rauntímaherkænskuleikinn StarCraft"],"dc:type":["Thesis"]},"updated_at":"2026-07-27T20:39:57Z"}