{"id":"https://openalex.org/W2131829828","doi":"https://doi.org/10.1109/irds.2002.1041682","title":"Cooperative behavior acquisition by asynchronous policy renewal that enables simultaneous learning in multiagent environment","display_name":"Cooperative behavior acquisition by asynchronous policy renewal that enables simultaneous learning in multiagent environment","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W2131829828","doi":"https://doi.org/10.1109/irds.2002.1041682","mag":"2131829828"},"language":"en","primary_location":{"id":"doi:10.1109/irds.2002.1041682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/irds.2002.1041682","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/RSJ International Conference on Intelligent Robots and System","raw_type":"proceedings-article"},"type":"conference-paper","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/A5053300819","display_name":"Shoichi Ikenoue","orcid":null},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"S. Ikenoue","raw_affiliation_strings":["Department of Adaptive Machine Systems, Osaka University, Osaka, Japan","[Department of Adaptive Machine Systems, Osaka University, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Adaptive Machine Systems, Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]},{"raw_affiliation_string":"[Department of Adaptive Machine Systems, Osaka University, Japan]","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044985800","display_name":"Minoru Asada","orcid":"https://orcid.org/0000-0001-9506-6333"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"M. Asada","raw_affiliation_strings":["Department of Adaptive Machine Systems, Osaka University, Osaka, Japan","[Department of Adaptive Machine Systems, Osaka University, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Adaptive Machine Systems, Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]},{"raw_affiliation_string":"[Department of Adaptive Machine Systems, Osaka University, Japan]","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072232488","display_name":"Koh Hosoda","orcid":"https://orcid.org/0000-0001-8392-1021"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Hosoda","raw_affiliation_strings":["Department of Adaptive Machine Systems, Osaka University, Osaka, Japan","[Department of Adaptive Machine Systems, Osaka University, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Adaptive Machine Systems, Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]},{"raw_affiliation_string":"[Department of Adaptive Machine Systems, Osaka University, Japan]","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98285908"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"2728","last_page":"2734"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9577999711036682,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9502999782562256,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.8407789468765259},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7230190634727478},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5148023962974548},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.4955507516860962},{"id":"https://openalex.org/keywords/asynchronous-learning","display_name":"Asynchronous learning","score":0.4388194680213928},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3981863558292389},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31767159700393677},{"id":"https://openalex.org/keywords/cooperative-learning","display_name":"Cooperative learning","score":0.21327298879623413},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1826038360595703},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14520779252052307},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12844526767730713},{"id":"https://openalex.org/keywords/synchronous-learning","display_name":"Synchronous learning","score":0.12715506553649902},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.07277029752731323}],"concepts":[{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.8407789468765259},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7230190634727478},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5148023962974548},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.4955507516860962},{"id":"https://openalex.org/C2777072894","wikidata":"https://www.wikidata.org/wiki/Q4812204","display_name":"Asynchronous learning","level":5,"score":0.4388194680213928},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3981863558292389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31767159700393677},{"id":"https://openalex.org/C51672120","wikidata":"https://www.wikidata.org/wiki/Q303446","display_name":"Cooperative learning","level":3,"score":0.21327298879623413},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1826038360595703},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14520779252052307},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12844526767730713},{"id":"https://openalex.org/C19122763","wikidata":"https://www.wikidata.org/wiki/Q7662215","display_name":"Synchronous learning","level":4,"score":0.12715506553649902},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.07277029752731323},{"id":"https://openalex.org/C88610354","wikidata":"https://www.wikidata.org/wiki/Q1813494","display_name":"Teaching method","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/irds.2002.1041682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/irds.2002.1041682","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/RSJ International Conference on Intelligent Robots and System","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":18,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W1501331554","https://openalex.org/W1511279904","https://openalex.org/W1542941925","https://openalex.org/W1557517019","https://openalex.org/W1641379095","https://openalex.org/W1681475672","https://openalex.org/W1919315941","https://openalex.org/W2006410236","https://openalex.org/W2121863487","https://openalex.org/W2155791599","https://openalex.org/W2167261463","https://openalex.org/W2914048451","https://openalex.org/W4214717370","https://openalex.org/W6630113399","https://openalex.org/W6683164292","https://openalex.org/W6759229479"],"related_works":["https://openalex.org/W4226047841","https://openalex.org/W2156559761","https://openalex.org/W3020208395","https://openalex.org/W2496167052","https://openalex.org/W2041343407","https://openalex.org/W2058515809","https://openalex.org/W4295242624","https://openalex.org/W2024923645","https://openalex.org/W2725154194","https://openalex.org/W2097058819"],"abstract_inverted_index":{"This":[0,57],"paper":[1],"presents":[2],"a":[3,134,142],"method":[4],"for":[5,28,46,76],"simultaneous":[6],"learning":[7,47,84],"in":[8,38,120,133],"multiagent":[9,136],"environment":[10],"to":[11,91,97,113,127],"facilitate":[12],"cooperative":[13,131],"behavior.":[14],"Each":[15],"agent":[16],"has":[17],"one":[18,21,128],"policy":[19],"and":[20,42,141],"action":[22,29,34,102,106],"value":[23,35,103],"function:":[24],"the":[25,33,39,43,50,54,64,69,77,83,93,115,130],"former":[26],"is":[27,45,139,144],"execution":[30],"based":[31,48,62],"on":[32,49,63,82],"function":[36],"updated":[37],"previous":[40],"stage,":[41],"latter":[44],"episodes":[51],"experienced":[52],"by":[53],"current":[55],"policy.":[56],"makes":[58],"all":[59],"agents":[60],"behave":[61],"fixed":[65],"policies,":[66],"so":[67],"that":[68,80],"non-Markovian":[70],"problem":[71],"can":[72],"be":[73],"avoided":[74],"except":[75],"update":[78],"periods":[79],"depend":[81],"progress":[85],"of":[86,101,129],"each":[87],"agent.":[88],"In":[89],"order":[90],"avoid":[92,114],"local":[94,121],"maxima":[95],"due":[96],"such":[98],"asynchronous":[99],"renewal":[100],"functions,":[104],"optimistic":[105],"values":[107],"are":[108],"given":[109],"initially,":[110],"which":[111],"helps":[112],"exploration":[116],"process":[117],"being":[118],"trapped":[119],"maxima.":[122],"The":[123],"experimental":[124],"results":[125],"applied":[126],"tasks":[132],"dynamic,":[135],"environment,":[137],"RoboCup,":[138],"shown":[140],"discussion":[143],"given.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}