{"id":"https://openalex.org/W2139810597","doi":"https://doi.org/10.1109/icsmc.2009.5345952","title":"Generation of roles in reinforcement learning considering redistribution of reward between agents","display_name":"Generation of roles in reinforcement learning considering redistribution of reward between agents","publication_year":2009,"publication_date":"2009-10-01","ids":{"openalex":"https://openalex.org/W2139810597","doi":"https://doi.org/10.1109/icsmc.2009.5345952","mag":"2139810597"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2009.5345952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2009.5345952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Systems, Man and Cybernetics","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/A5103625743","display_name":"Masayuki Nakahara","orcid":null},"institutions":[{"id":"https://openalex.org/I148798404","display_name":"Tokyo University of Technology","ror":"https://ror.org/021a26605","country_code":"JP","type":"education","lineage":["https://openalex.org/I148798404"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masayuki Nakahara","raw_affiliation_strings":["Graduate School of Bionics, Computer and Media Sciences, Tokyo University of Technology, Hachioji, Tokyo, Japan","Graduate School of Bionics, Computer and Media Sciences, Tokyo University of Technology, Hachioji, Tokyo#TAB#"],"affiliations":[{"raw_affiliation_string":"Graduate School of Bionics, Computer and Media Sciences, Tokyo University of Technology, Hachioji, Tokyo, Japan","institution_ids":["https://openalex.org/I148798404"]},{"raw_affiliation_string":"Graduate School of Bionics, Computer and Media Sciences, Tokyo University of Technology, Hachioji, Tokyo#TAB#","institution_ids":["https://openalex.org/I148798404"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112434511","display_name":"Yuko Osana","orcid":null},"institutions":[{"id":"https://openalex.org/I148798404","display_name":"Tokyo University of Technology","ror":"https://ror.org/021a26605","country_code":"JP","type":"education","lineage":["https://openalex.org/I148798404"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuko Osana","raw_affiliation_strings":["School of Computer Science, Tokyo University of Technology, Hachioji, Tokyo, Japan","School of Computer Science, Tokyo University of Technology, Hachioji, Tokyo"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Tokyo University of Technology, Hachioji, Tokyo, Japan","institution_ids":["https://openalex.org/I148798404"]},{"raw_affiliation_string":"School of Computer Science, Tokyo University of Technology, Hachioji, Tokyo","institution_ids":["https://openalex.org/I148798404"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103625743"],"corresponding_institution_ids":["https://openalex.org/I148798404"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13357471,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2259","last_page":"2264"},"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":0.9783999919891357,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9703999757766724,"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/redistribution","display_name":"Redistribution (election)","score":0.8477809429168701},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8272367715835571},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7198473215103149},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.49153122305870056},{"id":"https://openalex.org/keywords/reward-system","display_name":"Reward system","score":0.46612098813056946},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.43561336398124695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4140571057796478},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10526019334793091},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07422879338264465}],"concepts":[{"id":"https://openalex.org/C74080474","wikidata":"https://www.wikidata.org/wiki/Q7305975","display_name":"Redistribution (election)","level":3,"score":0.8477809429168701},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8272367715835571},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7198473215103149},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.49153122305870056},{"id":"https://openalex.org/C143661069","wikidata":"https://www.wikidata.org/wiki/Q670713","display_name":"Reward system","level":2,"score":0.46612098813056946},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.43561336398124695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4140571057796478},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10526019334793091},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07422879338264465},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2009.5345952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2009.5345952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Systems, Man and Cybernetics","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":8,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1549717253","https://openalex.org/W1557517019","https://openalex.org/W1995663008","https://openalex.org/W2121863487","https://openalex.org/W2292878638","https://openalex.org/W4214717370","https://openalex.org/W6632788068"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"In":[0,22,73],"this":[1],"paper,":[2],"we":[3,144],"propose":[4],"a":[5],"method":[6,149],"for":[7,114,160],"generating":[8],"roles":[9,68,128],"by":[10,59,92,133],"redistribution":[11,134,161],"of":[12,19,30,69,105,129,135,162],"reward":[13,33,44,61,82,91,136],"between":[14,137],"agents":[15,38,58,70,77,130,138],"in":[16,139],"reinforcement":[17],"learning":[18],"multiagent":[20],"system.":[21],"the":[23,40,60,67,74,89,94,100,103,140,147,156],"proposed":[24,75,141,148],"method,":[25,76],"there":[26],"are":[27,71,107,131],"two":[28,115],"kinds":[29],"reward;":[31],"(1)":[32,117],"obtained":[34,90],"from":[35,46,63,88],"environment":[36,106],"when":[37,102,155],"reach":[39],"goal":[41],"and":[42,66,121,125],"(2)":[43,122],"received":[45,62],"other":[47,57,64],"agents.":[48],"Agents":[49],"can":[50,78,150],"learn":[51,151],"actions":[52,98],"to":[53,83,86],"work":[54],"cooperatively":[55],"with":[56],"agents,":[65],"generated.":[72],"decide":[79],"how":[80],"much":[81],"which":[84],"agent":[85],"give":[87],"using":[93],"history":[95],"that":[96,127,146],"records":[97],"at":[99],"time":[101],"change":[104],"recognized.":[108],"We":[109],"carried":[110],"out":[111],"computer":[112],"experiments":[113],"tasks;":[116],"path":[118],"finding":[119],"problem":[120],"transportation":[123],"problem,":[124],"confirmed":[126,145],"generated":[132],"method.":[142],"Moreover,":[143],"as":[152,154],"similar":[153],"designer":[157],"decides":[158],"conditions":[159],"reward.":[163]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}