{"id":"https://openalex.org/W1974812331","doi":"https://doi.org/10.1109/icarcv.2006.345353","title":"Multi-Agent Reinforcement Learning: A Survey","display_name":"Multi-Agent Reinforcement Learning: A Survey","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W1974812331","doi":"https://doi.org/10.1109/icarcv.2006.345353","mag":"1974812331"},"language":"en","primary_location":{"id":"doi:10.1109/icarcv.2006.345353","doi":"https://doi.org/10.1109/icarcv.2006.345353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarcv.2006.345353","pdf_url":null,"source":{"id":"https://openalex.org/S4363608251","display_name":"International Conference on Control, Automation, Robotics and Vision (ICARCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 9th International Conference on Control, Automation, Robotics and Vision","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5058935509","display_name":"Lucian Bu\u015foniu","orcid":"https://orcid.org/0000-0001-8017-1296","observed_orcids":["https://orcid.org/0000-0001-8017-1296"]},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lucian Busoniu","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technology, Delft, CD, The Netherlands","[Delft Center for Systems and Control, Delft University of Technology]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Delft, CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"[Delft Center for Systems and Control, Delft University of Technology]","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084264842","display_name":"Robert Babu\u0161ka","orcid":"https://orcid.org/0000-0001-9578-8598","observed_orcids":["https://orcid.org/0000-0001-9578-8598"]},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Robert Babuska","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technology, Delft, CD, The Netherlands","[Delft Center for Systems and Control, Delft University of Technology]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Delft, CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"[Delft Center for Systems and Control, Delft University of Technology]","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026547410","display_name":"Bart De Schutter","orcid":"https://orcid.org/0000-0001-9867-6196","observed_orcids":["https://orcid.org/0000-0001-9867-6196"]},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Bart De Schutter","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technology, Delft, CD, The Netherlands","[Delft Center for Systems and Control, Delft University of Technology]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Delft, CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"[Delft Center for Systems and Control, Delft University of Technology]","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":1.2437,"has_fulltext":false,"cited_by_count":125,"citation_normalized_percentile":{"value":0.78145216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.0,"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/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.9900000095367432},{"id":"https://openalex.org/keywords/multi-agent-systems","display_name":"multi-agent systems","score":0.9409999847412109},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.8169999718666077},{"id":"https://openalex.org/keywords/learning-objectives","display_name":"learning objectives","score":0.8090000152587891},{"id":"https://openalex.org/keywords/distributed-control","display_name":"distributed control","score":0.8569999933242798},{"id":"https://openalex.org/keywords/robotics","display_name":"robotics","score":0.5410000085830688}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8745380640029907},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.7959827184677124},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.736945390701294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7226980924606323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6096757650375366},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5733032822608948},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5410133600234985},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.49746254086494446},{"id":"https://openalex.org/C2777026412","wikidata":"https://www.wikidata.org/wiki/Q2684591","display_name":"Statement (logic)","level":2,"score":0.48865655064582825},{"id":"https://openalex.org/C202532154","wikidata":"https://www.wikidata.org/wiki/Q4374193","display_name":"Problem statement","level":2,"score":0.4661724865436554},{"id":"https://openalex.org/C2778464652","wikidata":"https://www.wikidata.org/wiki/Q309849","display_name":"Open research","level":2,"score":0.4306563436985016},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40706706047058105},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3771864175796509},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3737240433692932},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3478343188762665},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.33673352003097534},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13712355494499207},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12545126676559448},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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":2,"locations":[{"id":"doi:10.1109/icarcv.2006.345353","doi":"https://doi.org/10.1109/icarcv.2006.345353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarcv.2006.345353","pdf_url":null,"source":{"id":"https://openalex.org/S4363608251","display_name":"International Conference on Control, Automation, Robotics and Vision (ICARCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 9th International Conference on Control, Automation, Robotics and Vision","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.383.6992","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.383.6992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcsc.tudelft.nl/~bdeschutter/pub/rep/06_025.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1497847676","https://openalex.org/W1502765764","https://openalex.org/W1521003796","https://openalex.org/W1551034208","https://openalex.org/W1560074431","https://openalex.org/W1607392272","https://openalex.org/W1830835471","https://openalex.org/W1966224968","https://openalex.org/W1973039793","https://openalex.org/W2045817941","https://openalex.org/W2065821056","https://openalex.org/W2085366587","https://openalex.org/W2097498347","https://openalex.org/W2103047651","https://openalex.org/W2103437045","https://openalex.org/W2103561211","https://openalex.org/W2104602264","https://openalex.org/W2107544712","https://openalex.org/W2116399160","https://openalex.org/W2117341272","https://openalex.org/W2118318536","https://openalex.org/W2120327309","https://openalex.org/W2120539414","https://openalex.org/W2120846115","https://openalex.org/W2121863487","https://openalex.org/W2125631327","https://openalex.org/W2130109466","https://openalex.org/W2136696289","https://openalex.org/W2138362680","https://openalex.org/W2142839172","https://openalex.org/W2145067550","https://openalex.org/W2148496763","https://openalex.org/W2148825261","https://openalex.org/W2164637474","https://openalex.org/W2169747811","https://openalex.org/W4214717370","https://openalex.org/W4255047891"],"related_works":["https://openalex.org/W7098557977","https://openalex.org/W7099980355","https://openalex.org/W2099618002","https://openalex.org/W6920475523","https://openalex.org/W1744965757","https://openalex.org/W7005533258","https://openalex.org/W2406159999","https://openalex.org/W7099729845","https://openalex.org/W7097395540","https://openalex.org/W7098755965"],"abstract_inverted_index":{"Multi-agent":[0],"systems":[1],"are":[2,106,112],"rapidly":[3],"finding":[4],"applications":[5],"in":[6,20],"a":[7,60,96],"variety":[8],"of":[9,33,56,63,81,87,99],"domains,":[10],"including":[11],"robotics,":[12],"distributed":[13],"control,":[14],"telecommunications,":[15],"economics.":[16],"Many":[17],"tasks":[18],"arising":[19],"these":[21],"domains":[22],"require":[23],"that":[24],"the":[25,34,53,57,82,85,88],"agents":[26],"learn":[27],"behaviors":[28],"online.":[29],"A":[30],"significant":[31],"part":[32],"research":[35,110],"on":[36,48],"multi-agent":[37,89],"learning":[38,41,58,90],"concerns":[39],"reinforcement":[40],"techniques.":[42],"However,":[43],"due":[44],"to":[45,76],"different":[46,64],"viewpoints":[47],"central":[49],"issues,":[50],"such":[51],"as":[52],"formal":[54],"statement":[55],"goal,":[59],"large":[61],"number":[62],"methods":[65],"and":[66,108],"approaches":[67],"have":[68],"been":[69],"introduced.":[70],"In":[71],"this":[72],"paper":[73],"we":[74],"aim":[75],"present":[77],"an":[78],"integrated":[79],"survey":[80],"field.":[83],"First,":[84],"issue":[86],"goal":[91],"is":[92,101],"discussed,":[93],"after":[94],"which":[95],"representative":[97],"selection":[98],"algorithms":[100],"reviewed.":[102],"Finally,":[103],"open":[104],"issues":[105],"identified":[107],"future":[109],"directions":[111],"outlined":[113]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":6}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}