{"id":"https://openalex.org/W2897283383","doi":"https://doi.org/10.1109/cig.2018.8490427","title":"Tabular Reinforcement Learning in Real-Time Strategy Games via Options","display_name":"Tabular Reinforcement Learning in Real-Time Strategy Games via Options","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2897283383","doi":"https://doi.org/10.1109/cig.2018.8490427","mag":"2897283383"},"language":"en","primary_location":{"id":"doi:10.1109/cig.2018.8490427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2018.8490427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Conference on Computational Intelligence and Games (CIG)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048925954","display_name":"Anderson Rocha Tavares","orcid":"https://orcid.org/0000-0002-8530-6468"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Anderson R. Tavares","raw_affiliation_strings":["Laboratory of Multidisciplinary Research in Games, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Laboratory of Multidisciplinary Research in Games, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073879771","display_name":"Luiz Chaimowicz","orcid":"https://orcid.org/0000-0001-8156-9941"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Luiz Chaimowicz","raw_affiliation_strings":["Laboratory of Multidisciplinary Research in Games, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Laboratory of Multidisciplinary Research in Games, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048925954"],"corresponding_institution_ids":["https://openalex.org/I110200422"],"apc_list":null,"apc_paid":null,"fwci":0.9773,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.82245964,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"529","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11674","display_name":"Sports Analytics and Performance","score":0.9763000011444092,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9007536768913269},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7972511649131775},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7605094909667969},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5532354116439819},{"id":"https://openalex.org/keywords/portfolio","display_name":"Portfolio","score":0.5319535732269287},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5136362910270691},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.47884130477905273},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45994940400123596},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.44973838329315186},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4051186740398407},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3366391658782959}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9007536768913269},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7972511649131775},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7605094909667969},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5532354116439819},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.5319535732269287},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5136362910270691},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.47884130477905273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45994940400123596},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.44973838329315186},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4051186740398407},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3366391658782959},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cig.2018.8490427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2018.8490427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Conference on Computational Intelligence and Games (CIG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.800000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1542941925","https://openalex.org/W1565097357","https://openalex.org/W1750339092","https://openalex.org/W2022504108","https://openalex.org/W2026615874","https://openalex.org/W2096287700","https://openalex.org/W2109910161","https://openalex.org/W2121863487","https://openalex.org/W2131600418","https://openalex.org/W2144445939","https://openalex.org/W2145339207","https://openalex.org/W2150823748","https://openalex.org/W2156078757","https://openalex.org/W2203132035","https://openalex.org/W2230033167","https://openalex.org/W2257979135","https://openalex.org/W2397240726","https://openalex.org/W2518713116","https://openalex.org/W2592215206","https://openalex.org/W2604283518","https://openalex.org/W2621262673","https://openalex.org/W2725258047","https://openalex.org/W2726569368","https://openalex.org/W2729668291","https://openalex.org/W2731936231","https://openalex.org/W2741302028","https://openalex.org/W2787259794","https://openalex.org/W2794254934","https://openalex.org/W2802184653","https://openalex.org/W2950040888","https://openalex.org/W2962789937","https://openalex.org/W2963262099","https://openalex.org/W3089351328","https://openalex.org/W3103780890","https://openalex.org/W4214717370","https://openalex.org/W4293862243","https://openalex.org/W4299335686","https://openalex.org/W6632558091","https://openalex.org/W6637770179","https://openalex.org/W6687917390","https://openalex.org/W6703271639","https://openalex.org/W6712173889","https://openalex.org/W6726754200","https://openalex.org/W6734325300","https://openalex.org/W6736622323","https://openalex.org/W6738940270","https://openalex.org/W6740416028","https://openalex.org/W6740468469","https://openalex.org/W6740590696","https://openalex.org/W6740780732","https://openalex.org/W6749876370","https://openalex.org/W6750809367","https://openalex.org/W6765378368","https://openalex.org/W6783356669"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894"],"abstract_inverted_index":{"Real-Time":[0],"Strategy":[1],"(RTS)":[2],"games":[3],"are":[4,41,50],"complex":[5],"domains":[6],"with":[7,52],"huge":[8],"state":[9,57],"and":[10,60],"action":[11],"spaces.":[12],"In":[13,29],"such":[14],"games,":[15],"humans":[16],"usually":[17],"pursue":[18],"long-term":[19],"plans,":[20],"which":[21,40,79],"take":[22],"long":[23],"sequences":[24],"of":[25,55,63,75],"actions":[26,43],"to":[27],"achieve.":[28],"this":[30,34],"work,":[31],"we":[32,67],"implement":[33],"behavior":[35],"by":[36],"reasoning":[37],"over":[38],"options,":[39],"temporally-extended":[42],"in":[44,86],"Markov":[45],"Decision":[46],"Processes.":[47],"Our":[48],"options":[49],"defined":[51],"the":[53,73],"aid":[54],"a":[56,61],"aggregation":[58],"scheme":[59],"portfolio":[62],"game-playing":[64],"algorithms.":[65],"Experimentally,":[66],"show":[68],"that":[69],"our":[70],"approach":[71],"leverages":[72],"capabilities":[74],"traditional":[76],"reinforcement-learning":[77],"techniques,":[78],"become":[80],"competitive":[81],"against":[82],"state-of-the-art":[83],"search":[84],"methods":[85],"\u03bcRTS.":[87]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}