{"id":"https://openalex.org/W2073900753","doi":"https://doi.org/10.1109/camsap.2013.6714066","title":"Distributed reinforcement learning in multi-agent networks","display_name":"Distributed reinforcement learning in multi-agent networks","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2073900753","doi":"https://doi.org/10.1109/camsap.2013.6714066","mag":"2073900753"},"language":"en","primary_location":{"id":"doi:10.1109/camsap.2013.6714066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/camsap.2013.6714066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 5th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)","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/A5077268766","display_name":"Soummya Kar","orcid":"https://orcid.org/0000-0002-8060-5581"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Soummya Kar","raw_affiliation_strings":["Department of ECE, Carnegie Mellon University, Pittsburgh, PA","[Dept. of ECE, Carnegie Mellon University, Pittsburgh, PA, USA]"],"affiliations":[{"raw_affiliation_string":"Department of ECE, Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Dept. of ECE, Carnegie Mellon University, Pittsburgh, PA, USA]","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045861415","display_name":"Jos\u00e9 M. F. Moura","orcid":"https://orcid.org/0000-0002-9822-8294"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jose M. F. Moura","raw_affiliation_strings":["Department of ECE, Carnegie Mellon University, Pittsburgh, PA","[Dept. of ECE, Carnegie Mellon University, Pittsburgh, PA, USA]"],"affiliations":[{"raw_affiliation_string":"Department of ECE, Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Dept. of ECE, Carnegie Mellon University, Pittsburgh, PA, USA]","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042307561","display_name":"H. Vincent Poor","orcid":"https://orcid.org/0000-0002-2062-131X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. Vincent Poor","raw_affiliation_strings":["Department of EE, Princeton University, Princeton, NJ","Dept. of EE, Princeton Univ., Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Department of EE, Princeton University, Princeton, NJ","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Dept. of EE, Princeton Univ., Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077268766"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.12789857,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"296","last_page":"299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9968000054359436,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8374965786933899},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7839164137840271},{"id":"https://openalex.org/keywords/stochastic-game","display_name":"Stochastic game","score":0.7529920935630798},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6597162485122681},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6585888862609863},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6335645914077759},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5168031454086304},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5137556791305542},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5084089636802673},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4689730405807495},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4404152035713196},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.43720391392707825},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4294532239437103},{"id":"https://openalex.org/keywords/distributed-algorithm","display_name":"Distributed algorithm","score":0.421298623085022},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3322943449020386},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.2812696695327759},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22880926728248596},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2015945315361023},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1448664665222168}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8374965786933899},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7839164137840271},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.7529920935630798},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6597162485122681},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6585888862609863},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6335645914077759},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5168031454086304},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5137556791305542},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5084089636802673},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4689730405807495},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4404152035713196},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.43720391392707825},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4294532239437103},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.421298623085022},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3322943449020386},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2812696695327759},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22880926728248596},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2015945315361023},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1448664665222168},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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},{"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},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/camsap.2013.6714066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/camsap.2013.6714066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 5th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1826343992","https://openalex.org/W1918371733","https://openalex.org/W1990005421","https://openalex.org/W2002444764","https://openalex.org/W2009022268","https://openalex.org/W2009533501","https://openalex.org/W2093103468","https://openalex.org/W2099618002","https://openalex.org/W2103561211","https://openalex.org/W2108306501","https://openalex.org/W2150147323","https://openalex.org/W4233696721","https://openalex.org/W6675356487","https://openalex.org/W6682198394"],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W2472051997","https://openalex.org/W2101748387","https://openalex.org/W4308702637","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2156021013","https://openalex.org/W2903299703","https://openalex.org/W1574958246"],"abstract_inverted_index":{"Distributed":[0],"reinforcement":[1],"learning":[2,53,98,139,176],"algorithms":[3,133,177],"for":[4,170],"collaborative":[5,163],"multi-agent":[6,119],"Markov":[7],"decision":[8,120],"processes":[9],"(MDPs)":[10],"are":[11,134,178],"presented":[12],"and":[13,40,66,107,122,155],"analyzed.":[14],"The":[15],"networked":[16],"setup":[17],"consists":[18],"of":[19,22,44,51,62,83,85,125,161,174],"a":[20,36,45],"collection":[21],"agents":[23],"(learners)":[24],"which":[25,92],"respond":[26],"differently":[27],"(depending":[28],"on":[29,117],"their":[30],"instantaneous":[31,104],"one-stage":[32],"random":[33],"costs)":[34],"to":[35,136,150],"global":[37,63],"controlled":[38],"state":[39,64],"the":[41,49,54,60,78,86,108,118,126,130,152,156,162,171],"control":[42,57,159],"actions":[43],"remote":[46],"controller.":[47],"With":[48],"objective":[50],"jointly":[52],"optimal":[55,138,157],"stationary":[56,158],"policy":[58,160],"(in":[59],"absence":[61],"transition":[65],"local":[67],"agent":[68,94,147],"cost":[69],"statistics)":[70],"that":[71],"minimizes":[72],"network-averaged":[73],"infinite":[74],"horizon":[75],"discounted":[76],"cost,":[77],"paper":[79],"presents":[80],"distributed":[81,132,175],"variants":[82],"Q-learning":[84],"consensus":[87],"+":[88],"innovations":[89],"type":[90],"in":[91],"each":[93,145],"sequentially":[95],"refines":[96],"its":[97,103],"parameters":[99],"by":[100],"locally":[101],"processing":[102],"payoff":[105],"data":[106],"information":[109],"received":[110],"from":[111],"neighboring":[112],"agents.":[113],"Under":[114],"broad":[115],"conditions":[116],"model":[121],"mean":[123],"connectivity":[124],"inter-agent":[127],"communication":[128],"network,":[129],"proposed":[131,172],"shown":[135,149],"achieve":[137],"asymptotically,":[140],"i.e.,":[141],"almost":[142],"surely":[143],"(a.s.)":[144],"network":[146],"is":[148],"learn":[151],"value":[153],"function":[154],"MDP":[164],"asymptotically.":[165],"Further,":[166],"convergence":[167],"rate":[168],"estimates":[169],"class":[173],"obtained.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}