{"id":"https://openalex.org/W2152835608","doi":"https://doi.org/10.1145/1553374.1553422","title":"Dynamic analysis of multiagent <i>Q</i> -learning with \u03b5-greedy exploration","display_name":"Dynamic analysis of multiagent <i>Q</i> -learning with \u03b5-greedy exploration","publication_year":2009,"publication_date":"2009-06-14","ids":{"openalex":"https://openalex.org/W2152835608","doi":"https://doi.org/10.1145/1553374.1553422","mag":"2152835608"},"language":"en","primary_location":{"id":"doi:10.1145/1553374.1553422","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","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/A5061153157","display_name":"Eduardo Rodrigues Gomes","orcid":"https://orcid.org/0000-0003-3595-312X"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Eduardo Rodrigues Gomes","raw_affiliation_strings":["Swinburne University of Technology, Hawthorn, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Swinburne University of Technology, Hawthorn, VIC, Australia","institution_ids":["https://openalex.org/I57093077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024220409","display_name":"Ryszard Kowalczyk","orcid":"https://orcid.org/0000-0003-0937-4028"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ryszard Kowalczyk","raw_affiliation_strings":["Swinburne University of Technology, Hawthorn, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Swinburne University of Technology, Hawthorn, VIC, Australia","institution_ids":["https://openalex.org/I57093077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061153157"],"corresponding_institution_ids":["https://openalex.org/I57093077"],"apc_list":null,"apc_paid":null,"fwci":10.0201,"has_fulltext":false,"cited_by_count":89,"citation_normalized_percentile":{"value":0.98323913,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"369","last_page":"376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9909999966621399,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9735999703407288,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.7633281946182251},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6789346933364868},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.6350027322769165},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.60163813829422},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5351223945617676},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4758703112602234},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.452555775642395},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.351759135723114},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18013259768486023},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14543139934539795}],"concepts":[{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.7633281946182251},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6789346933364868},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.6350027322769165},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.60163813829422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5351223945617676},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4758703112602234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.452555775642395},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.351759135723114},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18013259768486023},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14543139934539795},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1553374.1553422","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:researchbank.swinburne.edu.au:2e929880-bc0d-4ece-899c-b64ee9d9643e/1","is_oa":false,"landing_page_url":"http://hdl.handle.net/1959.3/68923","pdf_url":null,"source":{"id":"https://openalex.org/S4306401157","display_name":"Swinburne Research Bank (Swinburne University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I57093077","host_organization_name":"Swinburne University of Technology","host_organization_lineage":["https://openalex.org/I57093077"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"26th Annual International Conference on Machine Learning (ICML 2009), Montreal, Canada, 14-18 June 2009 / Leon Bottou and Michael Littman (eds.), Vol. 382, pp. 369-376","raw_type":"acceptedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W137071854","https://openalex.org/W1515851193","https://openalex.org/W1553414138","https://openalex.org/W1963754118","https://openalex.org/W1967250398","https://openalex.org/W1971681797","https://openalex.org/W1981707771","https://openalex.org/W1995622844","https://openalex.org/W2071983464","https://openalex.org/W2085728653","https://openalex.org/W2104602264","https://openalex.org/W2107544712","https://openalex.org/W2110052587","https://openalex.org/W2121863487","https://openalex.org/W2129095758","https://openalex.org/W2138076440","https://openalex.org/W2160846359","https://openalex.org/W2165284868","https://openalex.org/W3086549239","https://openalex.org/W3149412023","https://openalex.org/W4214717370","https://openalex.org/W6677916085"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2032233321"],"abstract_inverted_index":{"The":[0,97],"development":[1],"of":[2,11,27,40,55,65,82,94,99],"mechanisms":[3],"to":[4,36,88],"understand":[5],"and":[6,60,68],"model":[7,37,76],"the":[8,19,38,44,56,63,69,77,91,95,100,111],"expected":[9,92],"behaviour":[10,39,93],"multiagent":[12],"learners":[13],"is":[14,86,102],"becoming":[15],"increasingly":[16],"important":[17],"as":[18,79],"area":[20],"rapidly":[21],"find":[22],"application":[23],"in":[24,106],"a":[25,34,52,80],"variety":[26],"domains.":[28],"In":[29],"this":[30],"paper":[31],"we":[32,50],"present":[33],"framework":[35,101],"Q-learning":[41,57],"agents":[42,67],"using":[43],"o-greedy":[45,70],"exploration":[46],"mechanism.":[47],"For":[48],"this,":[49],"analyse":[51,90],"continuous-time":[53],"version":[54],"update":[58],"rule":[59],"study":[61],"how":[62],"presence":[64],"other":[66],"mechanism":[71],"affect":[72],"it.":[73],"We":[74],"then":[75],"problem":[78],"system":[81],"difference":[83],"equations":[84],"which":[85],"used":[87],"theoretically":[89],"agents.":[96],"applicability":[98],"tested":[103],"through":[104],"experiments":[105],"typical":[107],"games":[108],"selected":[109],"from":[110],"literature.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":9}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2016-06-24T00:00:00"}