{"id":"https://openalex.org/W4210642114","doi":"https://doi.org/10.1109/cdc45484.2021.9683607","title":"Distributed Consensus-Based Multi-Agent Off-Policy Temporal-Difference Learning","display_name":"Distributed Consensus-Based Multi-Agent Off-Policy Temporal-Difference Learning","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W4210642114","doi":"https://doi.org/10.1109/cdc45484.2021.9683607"},"language":"en","primary_location":{"id":"doi:10.1109/cdc45484.2021.9683607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683607","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2021 60th IEEE Conference on Decision and Control (CDC)","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/I170253739","display_name":"Singidunum University","ror":"https://ror.org/017v7rz39","country_code":"RS","type":"education","lineage":["https://openalex.org/I170253739"]},{"id":"https://openalex.org/I88596544","display_name":"Universidade Lus\u00f3fona","ror":"https://ror.org/05xxfer42","country_code":"PT","type":"education","lineage":["https://openalex.org/I88596544"]}],"countries":["PT","RS"],"is_corresponding":false,"raw_author_name":"Milos S. Stankovic","raw_affiliation_strings":["COPELABS, Universidade Lus\u00f3fona de Humanidades e Tecnologias, Lisboa, Portugal","University Singidunum, Belgrade, Serbia","Vlatacom Institute, Belgrade, Serbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"COPELABS, Universidade Lus\u00f3fona de Humanidades e Tecnologias, Lisboa, Portugal","institution_ids":["https://openalex.org/I88596544"]},{"raw_affiliation_string":"University Singidunum, Belgrade, Serbia","institution_ids":["https://openalex.org/I170253739"]},{"raw_affiliation_string":"Vlatacom Institute, Belgrade, Serbia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020552563","display_name":"Marko Beko","orcid":"https://orcid.org/0000-0001-7315-8739"},"institutions":[{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]},{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]},{"id":"https://openalex.org/I88596544","display_name":"Universidade Lus\u00f3fona","ror":"https://ror.org/05xxfer42","country_code":"PT","type":"education","lineage":["https://openalex.org/I88596544"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Marko Beko","raw_affiliation_strings":["COPELABS, Universidade Lus\u00f3fona de Humanidades e Tecnologias, Lisboa, Portugal","Instituto de Telecomunica\u00e7\u00f5es, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Lisbon, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"COPELABS, Universidade Lus\u00f3fona de Humanidades e Tecnologias, Lisboa, Portugal","institution_ids":["https://openalex.org/I88596544"]},{"raw_affiliation_string":"Instituto de Telecomunica\u00e7\u00f5es, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Lisbon, Portugal","institution_ids":["https://openalex.org/I4210120471","https://openalex.org/I141596103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018863930","display_name":"Srdjan Stankovi\u0107","orcid":"https://orcid.org/0000-0002-4795-494X"},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, University of Belgrade, Serbia","institution_ids":["https://openalex.org/I4068193"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8552,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.85866337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5976","last_page":"5981"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9994999766349792,"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":0.9994999766349792,"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/T13553","display_name":"Age of Information Optimization","score":0.9969000220298767,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965999722480774,"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/computer-science","display_name":"Computer science","score":0.6966623067855835},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6439706087112427},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5851870179176331},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5218573808670044},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4960702359676361},{"id":"https://openalex.org/keywords/consensus","display_name":"Consensus","score":0.4916568398475647},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.47162604331970215},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4575980305671692},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.43889251351356506},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4292655885219574},{"id":"https://openalex.org/keywords/distributed-learning","display_name":"Distributed learning","score":0.42527538537979126},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42371857166290283},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4208703637123108},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4075583517551422},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.35841578245162964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26112866401672363},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24664181470870972},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20409780740737915},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.10084843635559082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6966623067855835},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6439706087112427},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5851870179176331},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5218573808670044},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4960702359676361},{"id":"https://openalex.org/C107107730","wikidata":"https://www.wikidata.org/wiki/Q2994424","display_name":"Consensus","level":3,"score":0.4916568398475647},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.47162604331970215},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4575980305671692},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.43889251351356506},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4292655885219574},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.42527538537979126},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42371857166290283},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4208703637123108},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4075583517551422},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.35841578245162964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26112866401672363},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24664181470870972},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20409780740737915},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.10084843635559082},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc45484.2021.9683607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683607","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320329307","display_name":"Science Fund of the Republic of Serbia","ror":null},{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1098911146","https://openalex.org/W1499021337","https://openalex.org/W1547925194","https://openalex.org/W1918371733","https://openalex.org/W1941556277","https://openalex.org/W1979043738","https://openalex.org/W2024307985","https://openalex.org/W2044328306","https://openalex.org/W2075268401","https://openalex.org/W2077274021","https://openalex.org/W2123183226","https://openalex.org/W2137435346","https://openalex.org/W2139948925","https://openalex.org/W2144672231","https://openalex.org/W2154834860","https://openalex.org/W2166888056","https://openalex.org/W2267629510","https://openalex.org/W2286297039","https://openalex.org/W2504148212","https://openalex.org/W2559259492","https://openalex.org/W2776728688","https://openalex.org/W2947958009","https://openalex.org/W2949996623","https://openalex.org/W2953189830","https://openalex.org/W2962856794","https://openalex.org/W2963028406","https://openalex.org/W2964137650","https://openalex.org/W2966952338","https://openalex.org/W2991046523","https://openalex.org/W3010758700","https://openalex.org/W3103113203","https://openalex.org/W3135895062","https://openalex.org/W4205326910","https://openalex.org/W4206372735","https://openalex.org/W6632901617","https://openalex.org/W6640533243","https://openalex.org/W6677370284","https://openalex.org/W6695993938","https://openalex.org/W6752164047","https://openalex.org/W6762191990"],"related_works":["https://openalex.org/W2955790965","https://openalex.org/W2806157618","https://openalex.org/W3206576350","https://openalex.org/W4298064558","https://openalex.org/W2772472730","https://openalex.org/W2383312578","https://openalex.org/W2808418668","https://openalex.org/W3008618380","https://openalex.org/W2964123095","https://openalex.org/W2473364827"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,93],"propose":[4],"two":[5],"novel":[6],"distributed":[7],"consensus-based":[8],"temporal-difference":[9],"algorithms":[10,27,39,51,100],"for":[11],"multi-agent":[12],"off-policy":[13,38],"learning":[14],"of":[15,18,88],"linear":[16,46],"approximation":[17],"the":[19,65,86,89,99,113],"value":[20],"function":[21],"in":[22,62],"Markov":[23],"decision":[24],"processes.":[25],"The":[26,50,124],"are":[28,52,127],"composed":[29],"of:":[30],"1)":[31,56],"local":[32],"parameter":[33,115],"updates":[34],"based":[35],"on":[36,112],"single-agent":[37],"TD(\u03bb)":[40],"and":[41,43,59,73,122],"ETD(\u03bb),":[42],"2)":[44,60],"a":[45,80,104],"dynamic":[47],"consensus":[48,106],"scheme.":[49],"completely":[53,69],"decentralized,":[54],"allowing:":[55],"efficient":[57],"parallelization":[58],"applications":[61],"which":[63],"all":[64],"agents":[66],"may":[67],"have":[68],"different":[70,74],"behavior":[71],"policies":[72],"initial":[75],"state":[76],"distributions":[77],"while":[78],"evaluating":[79],"single":[81],"target":[82],"policy.":[83],"Starting":[84],"from":[85],"properties":[87,126],"underlying":[90],"Feller-Markov":[91],"processes,":[92],"show":[94],"that,":[95],"under":[96],"nonrestrictive":[97],"assumptions,":[98],"weakly":[101],"converge":[102],"to":[103],"unique":[105],"point.":[107],"A":[108],"discussion":[109],"is":[110],"given":[111],"asymptotic":[114],"values":[116],"at":[117],"consensus,":[118],"including":[119],"estimation":[120],"bias":[121],"variance.":[123],"algorithms\u2019":[125],"illustrated":[128],"by":[129],"characteristic":[130],"simulation":[131],"results.":[132]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}