{"id":"https://openalex.org/W2132522159","doi":"https://doi.org/10.1145/1082473.1082645","title":"Coordinated exploration in multi-agent reinforcement learning","display_name":"Coordinated exploration in multi-agent reinforcement learning","publication_year":2005,"publication_date":"2005-07-25","ids":{"openalex":"https://openalex.org/W2132522159","doi":"https://doi.org/10.1145/1082473.1082645","mag":"2132522159"},"language":"en","primary_location":{"id":"doi:10.1145/1082473.1082645","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1082473.1082645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth international joint conference on Autonomous agents and multiagent systems","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/A5013075653","display_name":"Katja Verbeeck","orcid":null},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Katja Verbeeck","raw_affiliation_strings":["Vrije Universiteit Brussel, Brussel, Belgium","Vrije Universiteit Brussel, Brussel, Belgium#TAB#"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Brussel, Brussel, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Vrije Universiteit Brussel, Brussel, Belgium#TAB#","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064553018","display_name":"Ann Now\u00e9","orcid":"https://orcid.org/0000-0001-6346-4564"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Ann Now\u00e9","raw_affiliation_strings":["Vrije Universiteit Brussel, Brussel, Belgium","Vrije Universiteit Brussel, Brussel, Belgium#TAB#"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Brussel, Brussel, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Vrije Universiteit Brussel, Brussel, Belgium#TAB#","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008547992","display_name":"Karl Tuyls","orcid":"https://orcid.org/0000-0001-7929-1944"},"institutions":[{"id":"https://openalex.org/I4210127597","display_name":"Transnational University Limburg","ror":"https://ror.org/02xyaf767","country_code":"BE","type":"education","lineage":["https://openalex.org/I4210127597"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Karl Tuyls","raw_affiliation_strings":["University of Limburg, Diepenbeek, Belgium"],"affiliations":[{"raw_affiliation_string":"University of Limburg, Diepenbeek, Belgium","institution_ids":["https://openalex.org/I4210127597"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013075653"],"corresponding_institution_ids":["https://openalex.org/I13469542"],"apc_list":null,"apc_paid":null,"fwci":3.4796,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.92392682,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1105","last_page":"1106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.8971999883651733,"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/T11182","display_name":"Auction Theory and Applications","score":0.8971999883651733,"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":0.8446000218391418,"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/T11675","display_name":"Open Source Software Innovations","score":0.779699981212616,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9213322401046753},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7644323706626892},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.6555074453353882},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5853111147880554},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5168752670288086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48311400413513184},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4697708785533905},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.4226866364479065},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09994766116142273}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9213322401046753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7644323706626892},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.6555074453353882},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5853111147880554},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5168752670288086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48311400413513184},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4697708785533905},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.4226866364479065},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09994766116142273},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1082473.1082645","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1082473.1082645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth international joint conference on Autonomous agents and multiagent systems","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":3,"referenced_works":["https://openalex.org/W1538558539","https://openalex.org/W2132022084","https://openalex.org/W6632269551"],"related_works":["https://openalex.org/W2371091044","https://openalex.org/W87513465","https://openalex.org/W2786230833","https://openalex.org/W2391666574","https://openalex.org/W3203256658","https://openalex.org/W2352650970","https://openalex.org/W1493952344","https://openalex.org/W4312372616","https://openalex.org/W8539471","https://openalex.org/W2061783822"],"abstract_inverted_index":{"This":[0],"paper":[1],"is":[2],"concerned":[3],"with":[4,67],"how":[5,95],"multi-agent":[6,21,46],"reinforcement":[7,85],"learning":[8],"algorithms":[9],"can":[10,40,98],"practically":[11],"be":[12],"applied":[13],"to":[14],"real-life":[15],"problems.":[16],"Recently,":[17],"a":[18,35,72,105,110,115],"new":[19],"coordinated":[20],"exploration":[22],"mechanism,":[23,34],"called":[24],"Exploring":[25],"Selfish":[26],"Reinforcement":[27],"Learning":[28],"(ESRL)":[29],"was":[30],"proposed.":[31],"With":[32],"this":[33],"group":[36],"of":[37,58,62,75,102],"independent":[38],"agents":[39,97],"find":[41],"optimal":[42],"fair":[43],"solutions":[44],"in":[45,104],"problems,":[47],"without":[48,55],"the":[49,56,60,63,79,89,100],"need":[50,57],"for":[51,82],"modeling":[52],"other":[53],"agents,":[54],"knowing":[59],"type":[61],"multiagent":[64],"problem":[65,101],"confronted":[66],"and":[68,113],"by":[69],"using":[70,83],"only":[71],"limited":[73],"form":[74],"communication.":[76],"In":[77],"particular,":[78],"mechanism":[80],"allows":[81],"natural":[84,106],"signals":[86],"coming":[87],"from":[88],"application":[90],"itself.":[91],"We":[92],"report":[93],"on":[94],"ESRL":[96],"solve":[99],"load-balancing":[103],"way,":[107],"both":[108],"as":[109,114],"common":[111],"interest":[112,117],"conflicting":[116],"problem.":[118]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}