{"id":"https://openalex.org/W2785556016","doi":"https://doi.org/10.1109/ssci.2017.8280949","title":"Cooperative reinforcement learning for multiple units combat in starCraft","display_name":"Cooperative reinforcement learning for multiple units combat in starCraft","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2785556016","doi":"https://doi.org/10.1109/ssci.2017.8280949","mag":"2785556016"},"language":"en","primary_location":{"id":"doi:10.1109/ssci.2017.8280949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci.2017.8280949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Symposium Series on Computational Intelligence (SSCI)","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/A5101787656","display_name":"Kun Shao","orcid":"https://orcid.org/0000-0003-0965-4302"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kun Shao","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080193690","display_name":"Yuanheng Zhu","orcid":"https://orcid.org/0000-0001-5384-423X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanheng Zhu","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101787656"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":2.5352,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.92074168,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"4","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9988999962806702,"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":0.9988999962806702,"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":0.986299991607666,"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":0.983299970626831,"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":0.872940182685852},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7174994349479675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5927736163139343},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5610844492912292},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5572510361671448},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5545458197593689},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5458387136459351},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.48105859756469727},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45613721013069153},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.45576605200767517},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4209126830101013},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3661671280860901},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1874869167804718},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1174689531326294},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09918355941772461}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.872940182685852},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7174994349479675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5927736163139343},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5610844492912292},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5572510361671448},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5545458197593689},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5458387136459351},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.48105859756469727},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45613721013069153},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.45576605200767517},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4209126830101013},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3661671280860901},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1874869167804718},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1174689531326294},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09918355941772461},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssci.2017.8280949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci.2017.8280949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1660754132","https://openalex.org/W1777239053","https://openalex.org/W1974221555","https://openalex.org/W1999035253","https://openalex.org/W2026615874","https://openalex.org/W2044504853","https://openalex.org/W2107726111","https://openalex.org/W2113913482","https://openalex.org/W2119324175","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2184201647","https://openalex.org/W2257979135","https://openalex.org/W2314323423","https://openalex.org/W2337268541","https://openalex.org/W2518713116","https://openalex.org/W2526283374","https://openalex.org/W2574978968","https://openalex.org/W2576264401","https://openalex.org/W2588283865","https://openalex.org/W2592798481","https://openalex.org/W2604283518","https://openalex.org/W2612780607","https://openalex.org/W2617547828","https://openalex.org/W2919115771","https://openalex.org/W2964223369","https://openalex.org/W4214717370","https://openalex.org/W4293862243","https://openalex.org/W4299335686","https://openalex.org/W6638088447","https://openalex.org/W6657105691","https://openalex.org/W6686067217","https://openalex.org/W6703383499","https://openalex.org/W6726754200","https://openalex.org/W6733825014","https://openalex.org/W6734678876","https://openalex.org/W6737726454"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"This":[0,41,78],"paper":[1,125],"presents":[2],"a":[3,69,95,108,136,145],"cooperative":[4,137],"reinforcement":[5],"learning":[6,104],"model":[7],"to":[8,25,82,92,101,133],"tackle":[9],"the":[10,28,32,53,57,62,103,112,116,141],"problem":[11,63],"of":[12,64],"multiple":[13],"units":[14,91,129],"combat":[15,39,134,152],"in":[16,38,123,135,144],"StarCraft.":[17],"We":[18,97],"construct":[19],"an":[20],"efficient":[21],"state":[22,34,45],"representation":[23],"method":[24,42],"break":[26],"down":[27],"complexity":[29],"caused":[30],"by":[31],"large":[33],"and":[35,46,56,66,86,88,106,139],"action":[36],"space":[37],"scenario.":[40,153],"takes":[43],"units'":[44,84],"various":[47],"distance":[48],"information":[49],"into":[50],"consideration,":[51],"including":[52,72],"current":[54],"step":[55],"last":[58],"step.":[59],"To":[60],"solve":[61],"sparse":[65],"delayed":[67],"rewards,":[68],"reward":[70,79],"function":[71,80,113],"small":[73],"intermediate":[74],"rewards":[75],"is":[76],"introduced.":[77],"helps":[81],"balance":[83],"move":[85],"attack,":[87],"encourages":[89],"our":[90,127],"fight":[93],"as":[94,111],"team.":[96],"present":[98],"gradient-descent":[99],"Sarsa(\u00c0)":[100],"train":[102],"model,":[105],"use":[107],"neural":[109],"network":[110],"approximator":[114],"for":[115],"Q":[117],"values.":[118],"The":[119],"experimental":[120],"results":[121],"presented":[122],"this":[124],"show":[126],"controlled":[128],"can":[130],"successfully":[131],"learn":[132],"way,":[138],"defeat":[140],"built-in":[142],"AI":[143],"3":[146],"Goliaths":[147],"against":[148],"6":[149],"Zealots":[150],"StarCraft":[151]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}