{"id":"https://openalex.org/W2963729301","doi":"https://doi.org/10.1109/mci.2019.2919363","title":"Improving RTS Game AI by Supervised Policy Learning, Tactical Search, and Deep Reinforcement Learning","display_name":"Improving RTS Game AI by Supervised Policy Learning, Tactical Search, and Deep Reinforcement Learning","publication_year":2019,"publication_date":"2019-07-16","ids":{"openalex":"https://openalex.org/W2963729301","doi":"https://doi.org/10.1109/mci.2019.2919363","mag":"2963729301"},"language":"en","primary_location":{"id":"doi:10.1109/mci.2019.2919363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mci.2019.2919363","pdf_url":null,"source":{"id":"https://openalex.org/S104797584","display_name":"IEEE Computational Intelligence Magazine","issn_l":"1556-603X","issn":["1556-603X","1556-6048"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computational Intelligence Magazine","raw_type":"journal-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/A5041783514","display_name":"Nicolas A. Barriga","orcid":"https://orcid.org/0000-0002-1914-3840"},"institutions":[{"id":"https://openalex.org/I134695357","display_name":"University of Talca","ror":"https://ror.org/01s4gpq44","country_code":"CL","type":"education","lineage":["https://openalex.org/I134695357"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Nicolas A. Barriga","raw_affiliation_strings":["School of Videogames Development and VR Engineering, Universidad de Talca, Talca, Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Videogames Development and VR Engineering, Universidad de Talca, Talca, Chile","institution_ids":["https://openalex.org/I134695357"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104093623","display_name":"Marius St\u0103nescu","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Marius Stanescu","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086109060","display_name":"Felipe Besoa\u00edn","orcid":"https://orcid.org/0000-0002-2810-9433"},"institutions":[{"id":"https://openalex.org/I134695357","display_name":"University of Talca","ror":"https://ror.org/01s4gpq44","country_code":"CL","type":"education","lineage":["https://openalex.org/I134695357"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Felipe Besoain","raw_affiliation_strings":["School of Videogames Development and VR Engineering, Universidad de Talca, Talca, Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Videogames Development and VR Engineering, Universidad de Talca, Talca, Chile","institution_ids":["https://openalex.org/I134695357"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031775706","display_name":"Michael Buro","orcid":"https://orcid.org/0000-0002-5382-7592"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Michael Buro","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3137,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.91175772,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"14","issue":"3","first_page":"8","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9994000196456909,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9994000196456909,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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/T11197","display_name":"Digital Games and Media","score":0.9754999876022339,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8379542231559753},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.831924557685852},{"id":"https://openalex.org/keywords/video-game","display_name":"Video game","score":0.6663289070129395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6230367422103882},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5245823264122009},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5109178423881531},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44989484548568726},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.44531044363975525},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37530234456062317},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.17291131615638733}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8379542231559753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.831924557685852},{"id":"https://openalex.org/C3018412434","wikidata":"https://www.wikidata.org/wiki/Q7889","display_name":"Video game","level":2,"score":0.6663289070129395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6230367422103882},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5245823264122009},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5109178423881531},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44989484548568726},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.44531044363975525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37530234456062317},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.17291131615638733},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mci.2019.2919363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mci.2019.2919363","pdf_url":null,"source":{"id":"https://openalex.org/S104797584","display_name":"IEEE Computational Intelligence Magazine","issn_l":"1556-603X","issn":["1556-603X","1556-6048"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computational Intelligence Magazine","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5099999904632568,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W1521891762","https://openalex.org/W1589331835","https://openalex.org/W1641379095","https://openalex.org/W1750339092","https://openalex.org/W1757796397","https://openalex.org/W1862134446","https://openalex.org/W1884151215","https://openalex.org/W2022504108","https://openalex.org/W2061902782","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2163605009","https://openalex.org/W2173564293","https://openalex.org/W2182353947","https://openalex.org/W2184201647","https://openalex.org/W2189058185","https://openalex.org/W2230033167","https://openalex.org/W2257979135","https://openalex.org/W2589422499","https://openalex.org/W2592798481","https://openalex.org/W2594794854","https://openalex.org/W2602425879","https://openalex.org/W2604283518","https://openalex.org/W2617547828","https://openalex.org/W2618530766","https://openalex.org/W2626637010","https://openalex.org/W2729651202","https://openalex.org/W2741302028","https://openalex.org/W2746553466","https://openalex.org/W2749807327","https://openalex.org/W2755694566","https://openalex.org/W2766199583","https://openalex.org/W2766447205","https://openalex.org/W2794254934","https://openalex.org/W2890388262","https://openalex.org/W2902955471","https://openalex.org/W2911296969","https://openalex.org/W2951799221","https://openalex.org/W2962938168","https://openalex.org/W2963022170","https://openalex.org/W2964043796","https://openalex.org/W2964056654","https://openalex.org/W2964345382","https://openalex.org/W3093287223","https://openalex.org/W4214717370","https://openalex.org/W4241119678","https://openalex.org/W4295598622","https://openalex.org/W4298857966","https://openalex.org/W6637770179","https://openalex.org/W6637967152","https://openalex.org/W6639006556","https://openalex.org/W6639268431","https://openalex.org/W6685444567","https://openalex.org/W6685683007","https://openalex.org/W6686067217","https://openalex.org/W6686898673","https://openalex.org/W6692846177","https://openalex.org/W6734678876","https://openalex.org/W6735011893","https://openalex.org/W6736622323","https://openalex.org/W6737849119","https://openalex.org/W6739516088","https://openalex.org/W6740857801","https://openalex.org/W6744400384","https://openalex.org/W6745787777","https://openalex.org/W6749304979","https://openalex.org/W6750253780","https://openalex.org/W6754417988","https://openalex.org/W6757146082","https://openalex.org/W6793907288"],"related_works":["https://openalex.org/W2116677773","https://openalex.org/W2155261584","https://openalex.org/W2584231425","https://openalex.org/W2042919702","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3167935049","https://openalex.org/W3029198973"],"abstract_inverted_index":{"Constructing":[0],"strong":[1,55],"AI":[2,63,211,246],"systems":[3,64],"for":[4,104,147],"video":[5,36,67,200],"games":[6,44],"is":[7,114],"difficult":[8],"due":[9],"to":[10,52,74,82,98,108,207,235],"enormous":[11],"state":[12,21],"and":[13,16,24,45,97,178,223,231],"action":[14,26,90,132],"spaces":[15],"the":[17,61,100,154,159,164,242],"lack":[18],"of":[19,30,88,173],"good":[20],"evaluation":[22],"functions":[23],"high-level":[25],"abstractions.":[27,133],"In":[28,69],"spite":[29],"recent":[31],"research":[32],"progress":[33],"in":[34,65,92,158,168,198,247],"popular":[35,215],"game":[37,105,120,161],"genres":[38],"such":[39,202,218],"as":[40,203,219],"Atari":[41],"2600":[42],"console":[43],"multiplayer":[46],"online":[47],"battle":[48],"arena":[49],"(MOBA)":[50],"games,":[51,96,201],"this":[53,70],"day":[54],"human":[56],"players":[57],"can":[58,144,195],"still":[59],"defeat":[60,241],"best":[62],"adversarial":[66],"games.":[68],"paper,":[71],"we":[72],"propose":[73],"use":[75,214],"a":[76,85,126,138,186],"deep":[77,191],"Convolutional":[78],"Neural":[79],"Network":[80],"(CNN)":[81],"select":[83],"among":[84],"limited":[86],"set":[87],"abstract":[89],"choices":[91],"Real-Time":[93],"Strategy":[94],"(RTS)":[95],"utilize":[99],"remaining":[101],"computation":[102],"time":[103,142],"tree":[106],"search":[107,128],"improve":[109,208],"low-level":[110],"tactics.":[111],"The":[112],"CNN":[113,139],"trained":[115],"by":[116,123,137],"supervised":[117],"learning":[118],"on":[119],"states":[121],"labeled":[122],"Puppet":[124,135],"Search,":[125],"strategic":[127,155],"algorithm":[129,166],"that":[130,143,163,188,240],"uses":[131],"Replacing":[134],"Search":[136],"frees":[140],"up":[141],"be":[145,196],"used":[146,197],"improving":[148],"units'":[149],"tactical":[150,209],"behavior":[151],"while":[152],"executing":[153],"plan.":[156],"Experiments":[157],"\u03bcRTS":[160,181],"show":[162],"combined":[165],"results":[167],"higher":[169],"win-rates":[170],"than":[171],"either":[172],"its":[174],"two":[175],"independent":[176],"components":[177],"other":[179],"state-of-the-art":[180],"agents.":[182],"We":[183,213],"then":[184],"present":[185],"case-study":[187],"investigates":[189],"how":[190],"Reinforcement":[192],"Learning":[193],"(RL)":[194],"modern":[199],"Total":[204],"War:":[205],"Warhammer,":[206],"multi-agent":[210],"modules.":[212],"RL":[216],"algorithms":[217],"Deep-Q":[220],"Networks":[221],"(DQN)":[222],"Asynchronous":[224],"AdvantageActor":[225],"Critic":[226],"(A3C),":[227],"basic":[228],"network":[229],"architectures":[230],"minimal":[232],"hyper-parameter":[233],"tuning":[234],"learn":[236],"complex":[237],"cooperative":[238],"behaviors":[239],"highest":[243],"difficulty":[244],"built-in":[245],"mediumscale":[248],"scenarios.":[249]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}