{"id":"https://openalex.org/W2096145798","doi":"https://doi.org/10.1017/s0269888912000057","title":"Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems","display_name":"Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems","publication_year":2012,"publication_date":"2012-02-22","ids":{"openalex":"https://openalex.org/W2096145798","doi":"https://doi.org/10.1017/s0269888912000057","mag":"2096145798"},"language":"en","primary_location":{"id":"doi:10.1017/s0269888912000057","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0269888912000057","pdf_url":null,"source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-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/A5062069838","display_name":"La\u00ebtitia Matignon","orcid":"https://orcid.org/0000-0001-7126-8715"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I37553959","display_name":"Universit\u00e9 de technologie de belfort-montb\u00e9liard","ror":"https://ror.org/05bn3m307","country_code":"FR","type":"education","lineage":["https://openalex.org/I37553959"]},{"id":"https://openalex.org/I2802759292","display_name":"Franche-Comt\u00e9 \u00c9lectronique M\u00e9canique Thermique et Optique - Sciences et Technologies","ror":"https://ror.org/004fmxv66","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I2802759292","https://openalex.org/I37553959","https://openalex.org/I4210095849","https://openalex.org/I4407990293","https://openalex.org/I53262699"]},{"id":"https://openalex.org/I53262699","display_name":"\u00c9cole Nationale Sup\u00e9rieure de M\u00e9canique et des Microtechniques","ror":"https://ror.org/05813w841","country_code":"FR","type":"education","lineage":["https://openalex.org/I53262699"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Laetitia Matignon","raw_affiliation_strings":["FEMTO-ST Institute, UMR CNRS 6174, UFC/ENSMM/UTBM, 24 rue Alain Savary, 25000 Besan\u00e7on, France","FEMTO-ST Institute, UMR CNRS 6174, UFC/ENSMM/UTBM, 24 rue Alain Savary, 25000 Besancon, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FEMTO-ST Institute, UMR CNRS 6174, UFC/ENSMM/UTBM, 24 rue Alain Savary, 25000 Besan\u00e7on, France","institution_ids":["https://openalex.org/I37553959","https://openalex.org/I53262699","https://openalex.org/I2802759292","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"FEMTO-ST Institute, UMR CNRS 6174, UFC/ENSMM/UTBM, 24 rue Alain Savary, 25000 Besancon, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086574604","display_name":"Guillaume J. Laurent","orcid":"https://orcid.org/0000-0003-3586-4696"},"institutions":[{"id":"https://openalex.org/I53262699","display_name":"\u00c9cole Nationale Sup\u00e9rieure de M\u00e9canique et des Microtechniques","ror":"https://ror.org/05813w841","country_code":"FR","type":"education","lineage":["https://openalex.org/I53262699"]},{"id":"https://openalex.org/I37553959","display_name":"Universit\u00e9 de technologie de belfort-montb\u00e9liard","ror":"https://ror.org/05bn3m307","country_code":"FR","type":"education","lineage":["https://openalex.org/I37553959"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2802759292","display_name":"Franche-Comt\u00e9 \u00c9lectronique M\u00e9canique Thermique et Optique - Sciences et Technologies","ror":"https://ror.org/004fmxv66","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I2802759292","https://openalex.org/I37553959","https://openalex.org/I4210095849","https://openalex.org/I4407990293","https://openalex.org/I53262699"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Guillaume J. Laurent","raw_affiliation_strings":["FEMTO-ST Institute, UMR CNRS 6174, UFC/ENSMM/UTBM, 24 rue Alain Savary, 25000 Besan\u00e7on, France","FEMTO-ST Institute, UMR CNRS 6174, UFC/ENSMM/UTBM, 24 rue Alain Savary, 25000 Besancon, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FEMTO-ST Institute, UMR CNRS 6174, UFC/ENSMM/UTBM, 24 rue Alain Savary, 25000 Besan\u00e7on, France","institution_ids":["https://openalex.org/I37553959","https://openalex.org/I53262699","https://openalex.org/I2802759292","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"FEMTO-ST Institute, UMR CNRS 6174, UFC/ENSMM/UTBM, 24 rue Alain Savary, 25000 Besancon, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108721234","display_name":"Nadine Le Fort-Piat","orcid":null},"institutions":[{"id":"https://openalex.org/I37553959","display_name":"Universit\u00e9 de technologie de belfort-montb\u00e9liard","ror":"https://ror.org/05bn3m307","country_code":"FR","type":"education","lineage":["https://openalex.org/I37553959"]},{"id":"https://openalex.org/I2802759292","display_name":"Franche-Comt\u00e9 \u00c9lectronique M\u00e9canique Thermique et Optique - Sciences et Technologies","ror":"https://ror.org/004fmxv66","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I2802759292","https://openalex.org/I37553959","https://openalex.org/I4210095849","https://openalex.org/I4407990293","https://openalex.org/I53262699"]},{"id":"https://openalex.org/I53262699","display_name":"\u00c9cole Nationale Sup\u00e9rieure de M\u00e9canique et des Microtechniques","ror":"https://ror.org/05813w841","country_code":"FR","type":"education","lineage":["https://openalex.org/I53262699"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Nadine Le Fort-Piat","raw_affiliation_strings":["FEMTO-ST Institute, UMR CNRS 6174, UFC/ENSMM/UTBM, 24 rue Alain Savary, 25000 Besan\u00e7on, France","FEMTO-ST Institute, UMR CNRS 6174, UFC/ENSMM/UTBM, 24 rue Alain Savary, 25000 Besancon, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FEMTO-ST Institute, UMR CNRS 6174, UFC/ENSMM/UTBM, 24 rue Alain Savary, 25000 Besan\u00e7on, France","institution_ids":["https://openalex.org/I37553959","https://openalex.org/I53262699","https://openalex.org/I2802759292","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"FEMTO-ST Institute, UMR CNRS 6174, UFC/ENSMM/UTBM, 24 rue Alain Savary, 25000 Besancon, France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062069838","https://openalex.org/A5086574604","https://openalex.org/A5108721234"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2802759292","https://openalex.org/I37553959","https://openalex.org/I53262699"],"apc_list":null,"apc_paid":null,"fwci":6.6304,"has_fulltext":false,"cited_by_count":429,"citation_normalized_percentile":{"value":0.96623293,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"27","issue":"1","first_page":"1","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11031","display_name":"Game Theory and Applications","score":0.9884999990463257,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8409904837608337},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7429019212722778},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.49510326981544495},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4691053032875061},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46808892488479614},{"id":"https://openalex.org/keywords/coordination-game","display_name":"Coordination game","score":0.44825243949890137},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4389817714691162},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3313950300216675},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.27599388360977173},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11956584453582764}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8409904837608337},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7429019212722778},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.49510326981544495},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4691053032875061},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46808892488479614},{"id":"https://openalex.org/C107257861","wikidata":"https://www.wikidata.org/wiki/Q656316","display_name":"Coordination game","level":2,"score":0.44825243949890137},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4389817714691162},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3313950300216675},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.27599388360977173},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11956584453582764},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s0269888912000057","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0269888912000057","pdf_url":null,"source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W56117469","https://openalex.org/W137071854","https://openalex.org/W178386168","https://openalex.org/W1484740474","https://openalex.org/W1521003796","https://openalex.org/W1527663244","https://openalex.org/W1557517019","https://openalex.org/W1560074431","https://openalex.org/W1569074635","https://openalex.org/W1579184372","https://openalex.org/W1583408742","https://openalex.org/W1590759229","https://openalex.org/W1605941417","https://openalex.org/W1606829969","https://openalex.org/W1639167632","https://openalex.org/W1641379095","https://openalex.org/W1825174002","https://openalex.org/W1835254890","https://openalex.org/W1972847450","https://openalex.org/W1973039793","https://openalex.org/W1977031068","https://openalex.org/W1980358463","https://openalex.org/W1987864653","https://openalex.org/W2008134955","https://openalex.org/W2045817941","https://openalex.org/W2049411421","https://openalex.org/W2050124350","https://openalex.org/W2060726785","https://openalex.org/W2065821056","https://openalex.org/W2067050450","https://openalex.org/W2074458475","https://openalex.org/W2081525555","https://openalex.org/W2085366587","https://openalex.org/W2091299493","https://openalex.org/W2099618002","https://openalex.org/W2104144149","https://openalex.org/W2104212358","https://openalex.org/W2104602264","https://openalex.org/W2105643086","https://openalex.org/W2107726111","https://openalex.org/W2108449787","https://openalex.org/W2108892923","https://openalex.org/W2109100253","https://openalex.org/W2120327309","https://openalex.org/W2120846115","https://openalex.org/W2121863487","https://openalex.org/W2136934807","https://openalex.org/W2138076440","https://openalex.org/W2138362680","https://openalex.org/W2139160917","https://openalex.org/W2142839172","https://openalex.org/W2147492008","https://openalex.org/W2150339816","https://openalex.org/W2152835608","https://openalex.org/W2152974163","https://openalex.org/W2154897200","https://openalex.org/W2155777776","https://openalex.org/W2156060009","https://openalex.org/W2161061197","https://openalex.org/W2168163987","https://openalex.org/W2171234133","https://openalex.org/W2575731723","https://openalex.org/W2595697910","https://openalex.org/W2801194081","https://openalex.org/W3105048218","https://openalex.org/W4214717370","https://openalex.org/W4247548111","https://openalex.org/W4254547512","https://openalex.org/W4285719527","https://openalex.org/W6628916341","https://openalex.org/W6631137000","https://openalex.org/W6634952046","https://openalex.org/W6635285615","https://openalex.org/W6636339474","https://openalex.org/W6647431038","https://openalex.org/W6675478397","https://openalex.org/W6678168664","https://openalex.org/W6680209877","https://openalex.org/W6680502337","https://openalex.org/W6681246212","https://openalex.org/W6685183561"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W3201878770","https://openalex.org/W2145363145","https://openalex.org/W2101748387","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W4206669594","https://openalex.org/W4319083788","https://openalex.org/W4226437174","https://openalex.org/W2032626653"],"abstract_inverted_index":{"Abstract":[0],"In":[1],"the":[2,31,68,106,116,126,134,140],"framework":[3],"of":[4,33,45,70,73,105,142],"fully":[5],"cooperative":[6],"multi-agent":[7,46,155],"systems,":[8],"independent":[9,34,76],"(non-communicative)":[10],"agents":[11],"that":[12,146],"learn":[13],"by":[14],"reinforcement":[15,77],"must":[16],"overcome":[17,147],"several":[18,27],"difficulties":[19],"to":[20,22,51],"manage":[21],"coordinate.":[23],"This":[24],"paper":[25,117],"identifies":[26],"challenges":[28,136],"responsible":[29],"for":[30,75,124,129],"non-coordination":[32],"agents:":[35],"Pareto-selection,":[36],"non-stationarity,":[37],"stochasticity,":[38],"alter-exploration":[39],"and":[40,62,97,110,118,150],"shadowed":[41],"equilibria.":[42],"A":[43],"selection":[44],"domains":[47,61],"is":[48,79],"classified":[49],"according":[50],"those":[52],"challenges:":[53],"matrix":[54],"games,":[55],"Boutilier's":[56],"coordination":[57],"game,":[58],"predators":[59],"pursuit":[60],"a":[63,71,122,130],"special":[64],"multi-state":[65],"game.":[66],"Moreover,":[67],"performance":[69,153],"range":[72],"algorithms":[74,83,145],"learners":[78],"evaluated":[80],"empirically.":[81],"Those":[82],"are":[84],"Q-learning":[85],"variants:":[86],"decentralized":[87],"Q-learning,":[88,90,92],"distributed":[89],"hysteretic":[91],"recursive":[93],"frequency":[94],"maximum":[95],"Q-value":[96],"win-or-learn":[98],"fast":[99],"policy":[100],"hill":[101],"climbing.":[102],"An":[103],"overview":[104],"learning":[107,144],"algorithms\u2019":[108],"strengths":[109],"weaknesses":[111],"against":[112],"each":[113],"challenge":[114],"concludes":[115],"can":[119],"serve":[120],"as":[121],"basis":[123],"choosing":[125],"appropriate":[127],"algorithm":[128],"new":[131,143],"domain.":[132],"Furthermore,":[133],"distilled":[135],"may":[137],"assist":[138],"in":[139,154],"design":[141],"these":[148],"problems":[149],"achieve":[151],"higher":[152],"applications.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":37},{"year":2024,"cited_by_count":44},{"year":2023,"cited_by_count":52},{"year":2022,"cited_by_count":55},{"year":2021,"cited_by_count":79},{"year":2020,"cited_by_count":54},{"year":2019,"cited_by_count":46},{"year":2018,"cited_by_count":26},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-19T08:33:51.333923","created_date":"2025-10-10T00:00:00"}