{"id":"https://openalex.org/W2504148212","doi":"https://doi.org/10.1109/acc.2016.7524910","title":"Multi-agent temporal-difference learning with linear function approximation: Weak convergence under time-varying network topologies","display_name":"Multi-agent temporal-difference learning with linear function approximation: Weak convergence under time-varying network topologies","publication_year":2016,"publication_date":"2016-07-01","ids":{"openalex":"https://openalex.org/W2504148212","doi":"https://doi.org/10.1109/acc.2016.7524910","mag":"2504148212"},"language":"en","primary_location":{"id":"doi:10.1109/acc.2016.7524910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2016.7524910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 American Control Conference (ACC)","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/A5055532417","display_name":"Milo\u0161 S. Stankovi\u0107","orcid":"https://orcid.org/0000-0001-9064-7059"},"institutions":[{"id":"https://openalex.org/I4068193","display_name":"University of Belgrade","ror":"https://ror.org/02qsmb048","country_code":"RS","type":"education","lineage":["https://openalex.org/I4068193"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Milos S. Stankovic","raw_affiliation_strings":["Innovation Center, University of Belgrade, Serbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovation Center, University of Belgrade, Serbia","institution_ids":["https://openalex.org/I4068193"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103386989","display_name":"Srdjan S. Stankovi\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I4068193","display_name":"University of Belgrade","ror":"https://ror.org/02qsmb048","country_code":"RS","type":"education","lineage":["https://openalex.org/I4068193"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Srdjan S. Stankovic","raw_affiliation_strings":["School of Electrical Engineering, University of Belgrade, Serbia","Vlatacom Institute, Belgrade, Serbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, University of Belgrade, Serbia","institution_ids":["https://openalex.org/I4068193"]},{"raw_affiliation_string":"Vlatacom Institute, Belgrade, Serbia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9544,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.91948184,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"167","last_page":"172"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11347","display_name":"Neural Networks Stability and Synchronization","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.6982643604278564},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6266903877258301},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5947777032852173},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.594364583492279},{"id":"https://openalex.org/keywords/ode","display_name":"Ode","score":0.57557213306427},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5362927317619324},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5126065611839294},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.493186891078949},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.4863503575325012},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4583728611469269},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.44658803939819336},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.44655197858810425},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4412746727466583},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.37816280126571655},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3667735457420349},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3550637364387512},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.2299608290195465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17409849166870117},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14164254069328308}],"concepts":[{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.6982643604278564},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6266903877258301},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5947777032852173},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.594364583492279},{"id":"https://openalex.org/C34862557","wikidata":"https://www.wikidata.org/wiki/Q178985","display_name":"Ode","level":2,"score":0.57557213306427},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5362927317619324},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5126065611839294},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.493186891078949},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.4863503575325012},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4583728611469269},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.44658803939819336},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.44655197858810425},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4412746727466583},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.37816280126571655},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3667735457420349},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3550637364387512},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.2299608290195465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17409849166870117},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14164254069328308},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acc.2016.7524910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2016.7524910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1098911146","https://openalex.org/W1499021337","https://openalex.org/W1547358136","https://openalex.org/W1576452626","https://openalex.org/W1600046456","https://openalex.org/W1646707810","https://openalex.org/W1706236309","https://openalex.org/W1918371733","https://openalex.org/W1976516240","https://openalex.org/W1979043738","https://openalex.org/W2015348855","https://openalex.org/W2024307985","https://openalex.org/W2028706574","https://openalex.org/W2044212084","https://openalex.org/W2044328306","https://openalex.org/W2075268401","https://openalex.org/W2077274021","https://openalex.org/W2094364653","https://openalex.org/W2099618002","https://openalex.org/W2121863487","https://openalex.org/W2123183226","https://openalex.org/W2137435346","https://openalex.org/W2144408773","https://openalex.org/W2144672231","https://openalex.org/W2154834860","https://openalex.org/W2160643434","https://openalex.org/W2166888056","https://openalex.org/W2962856794","https://openalex.org/W3103113203","https://openalex.org/W4214717370","https://openalex.org/W6635798015"],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W4308702637","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2903299703","https://openalex.org/W2016648086","https://openalex.org/W2156021013","https://openalex.org/W2083611438","https://openalex.org/W2042946219"],"abstract_inverted_index":{"In":[0],"this":[1,124],"paper":[2],"we":[3,94],"propose":[4],"two":[5],"novel":[6],"distributed":[7,50],"algorithms":[8,22,51,98,144],"for":[9,96],"iterative":[10],"multi-agent":[11],"off-policy":[12],"linear":[13,72],"value":[14,76],"function":[15],"approximation":[16],"in":[17],"Markov":[18],"decision":[19],"processes.":[20],"The":[21,48,136],"do":[23],"not":[24],"require":[25],"any":[26],"fusion":[27],"center":[28],"and":[29,86,138],"are":[30,145],"based":[31],"on":[32,81,147],"incorporating":[33],"consensus-based":[34],"collaborations":[35],"between":[36],"the":[37,53,62,70,75,82,87,92,102,119,132,139,142],"agents":[38,54,93],"over":[39],"time-varying":[40,83],"communication":[41],"networks":[42],"into":[43],"recently":[44],"proposed":[45,143],"single-agent":[46],"algorithms.":[47],"resulting":[49],"allow":[52],"to":[55,64,105,129],"have":[56],"different":[57],"behavior":[58],"policies":[59],"while":[60],"evaluating":[61],"response":[63],"a":[65,106,115],"single":[66],"target":[67],"policy,":[68],"using":[69],"same":[71],"parametrization":[73],"of":[74,91,101,118,141],"function.":[77],"Under":[78],"appropriate":[79],"assumptions":[80],"network":[84,120],"topology":[85],"overall":[88],"state-visiting":[89],"distributions":[90],"prove":[95],"both":[97],"weak":[99],"convergence":[100],"parameter":[103],"estimates":[104],"consensus":[107],"point":[108,125],"determined":[109],"by":[110],"an":[111,148],"associated":[112],"ODE.":[113],"By":[114],"proper":[116],"design":[117],"parameters":[121],"and/or":[122],"topology,":[123],"can":[126],"be":[127],"tuned":[128],"coincide":[130],"with":[131],"globally":[133],"optimal":[134],"point.":[135],"properties":[137],"effectiveness":[140],"illustrated":[146],"example.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}