{"id":"https://openalex.org/W3119097918","doi":"https://doi.org/10.1109/tac.2021.3049345","title":"Finite-Sample Analysis for Decentralized Batch Multiagent Reinforcement Learning With Networked Agents","display_name":"Finite-Sample Analysis for Decentralized Batch Multiagent Reinforcement Learning With Networked Agents","publication_year":2021,"publication_date":"2021-01-05","ids":{"openalex":"https://openalex.org/W3119097918","doi":"https://doi.org/10.1109/tac.2021.3049345","mag":"3119097918"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2021.3049345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2021.3049345","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","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/A5047410441","display_name":"Kaiqing Zhang","orcid":"https://orcid.org/0000-0002-7446-7581"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kaiqing Zhang","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL, USA","[Electrical and Computer Engineering, University of Illinois at Urbana-Champaign (UIUC), Urbana, Illinois, United States of America, 61801 (e-mail: kzhang66@illinois.edu)]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[Electrical and Computer Engineering, University of Illinois at Urbana-Champaign (UIUC), Urbana, Illinois, United States of America, 61801 (e-mail: kzhang66@illinois.edu)]","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727948","display_name":"Zhuoran Yang","orcid":"https://orcid.org/0000-0001-5269-9958"},"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":"Zhuoran Yang","raw_affiliation_strings":["Department of Operations Research and Financial Engineering, Princeton University, Princeton, NJ, USA","[Operations research and financial engineering, Princeton University, Princeton, NJ, United States of America, 08544 (e-mail: zy6@princeton.edu)]"],"affiliations":[{"raw_affiliation_string":"Department of Operations Research and Financial Engineering, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"[Operations research and financial engineering, Princeton University, Princeton, NJ, United States of America, 08544 (e-mail: zy6@princeton.edu)]","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349037","display_name":"Han Liu","orcid":"https://orcid.org/0000-0002-2470-1755"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Liu","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science and Statistics, Northwestern University, Evanston, IL, USA","[Northwestern University, United States of America, (e-mail: hanliu@northwestern.edu)]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science and Statistics, Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"[Northwestern University, United States of America, (e-mail: hanliu@northwestern.edu)]","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378792","display_name":"Tong Zhang","orcid":"https://orcid.org/0000-0002-5511-2558"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tong Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019604570","display_name":"Tamer Ba\u015far","orcid":"https://orcid.org/0000-0003-4406-7875"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tamer Basar","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL, USA","[Dept. of ECE & Coordinated Science Lab, Univ of Illinois, Urbana-Champaign, Urbana, IL, United States of America, 61801-2307 (e-mail: basar1@illinois.edu)]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[Dept. of ECE & Coordinated Science Lab, Univ of Illinois, Urbana-Champaign, Urbana, IL, United States of America, 61801-2307 (e-mail: basar1@illinois.edu)]","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047410441"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":3.5513,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.93395721,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"66","issue":"12","first_page":"5925","last_page":"5940"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9937999844551086,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9937999844551086,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.992900013923645,"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":0.9878000020980835,"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/marl","display_name":"Marl","score":0.8249589204788208},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.815311074256897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6437842845916748},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6428499221801758},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.437033087015152},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3920690417289734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2838156819343567},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26687902212142944}],"concepts":[{"id":"https://openalex.org/C92927620","wikidata":"https://www.wikidata.org/wiki/Q184053","display_name":"Marl","level":3,"score":0.8249589204788208},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.815311074256897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6437842845916748},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6428499221801758},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.437033087015152},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3920690417289734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2838156819343567},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26687902212142944},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tac.2021.3049345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2021.3049345","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-109143","is_oa":false,"landing_page_url":"http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=000725800500024","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:repository.ust.hk:1783.1-109143","is_oa":false,"landing_page_url":"http://repository.ust.hk/ir/Record/1783.1-109143","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G5364588660","display_name":null,"funder_award_id":"FA9550-19-1-0353","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":87,"referenced_works":["https://openalex.org/W107583932","https://openalex.org/W166862392","https://openalex.org/W1519783625","https://openalex.org/W1521003796","https://openalex.org/W1534630452","https://openalex.org/W1542941925","https://openalex.org/W1544761168","https://openalex.org/W1580572138","https://openalex.org/W1607392272","https://openalex.org/W1626977535","https://openalex.org/W1788877992","https://openalex.org/W1793264465","https://openalex.org/W1889629917","https://openalex.org/W1918371733","https://openalex.org/W1990199628","https://openalex.org/W2005437559","https://openalex.org/W2019338681","https://openalex.org/W2032631296","https://openalex.org/W2058239479","https://openalex.org/W2058557460","https://openalex.org/W2086977346","https://openalex.org/W2099618002","https://openalex.org/W2104753538","https://openalex.org/W2108383324","https://openalex.org/W2117355432","https://openalex.org/W2122701159","https://openalex.org/W2123447947","https://openalex.org/W2124144580","https://openalex.org/W2139418546","https://openalex.org/W2146890818","https://openalex.org/W2160135758","https://openalex.org/W2295652899","https://openalex.org/W2395162158","https://openalex.org/W2788115019","https://openalex.org/W2794842761","https://openalex.org/W2890347272","https://openalex.org/W2946912408","https://openalex.org/W2947958009","https://openalex.org/W2963028406","https://openalex.org/W2963649943","https://openalex.org/W2963748878","https://openalex.org/W2964123095","https://openalex.org/W2964137440","https://openalex.org/W2964191473","https://openalex.org/W2970884920","https://openalex.org/W3006140144","https://openalex.org/W3132503596","https://openalex.org/W3154844346","https://openalex.org/W4249154916","https://openalex.org/W4254547512","https://openalex.org/W4288602110","https://openalex.org/W4297789683","https://openalex.org/W4298064558","https://openalex.org/W4299802797","https://openalex.org/W6604362843","https://openalex.org/W6631137000","https://openalex.org/W6631168379","https://openalex.org/W6632004249","https://openalex.org/W6632768901","https://openalex.org/W6634770748","https://openalex.org/W6636288269","https://openalex.org/W6636868823","https://openalex.org/W6638036514","https://openalex.org/W6639430172","https://openalex.org/W6676468133","https://openalex.org/W6677549092","https://openalex.org/W6678481081","https://openalex.org/W6678494045","https://openalex.org/W6678573530","https://openalex.org/W6683733446","https://openalex.org/W6684470913","https://openalex.org/W6711807133","https://openalex.org/W6718904444","https://openalex.org/W6738796088","https://openalex.org/W6743367460","https://openalex.org/W6747035473","https://openalex.org/W6749032143","https://openalex.org/W6749163520","https://openalex.org/W6751658861","https://openalex.org/W6754906582","https://openalex.org/W6756545998","https://openalex.org/W6758937863","https://openalex.org/W6762191990","https://openalex.org/W6762605629","https://openalex.org/W6766343273","https://openalex.org/W6767019260","https://openalex.org/W6842827040"],"related_works":["https://openalex.org/W2126019709","https://openalex.org/W1702901972","https://openalex.org/W4249798507","https://openalex.org/W2069775250","https://openalex.org/W2152754392","https://openalex.org/W2196316523","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"Despite":[0],"the":[1,67,87,105,109,118,121,129,134,138,145,171,189],"increasing":[2],"interest":[3],"in":[4,9,61,86,99,163,188],"multiagent":[5],"reinforcement":[6,150],"learning":[7],"(MARL)":[8],"multiple":[10],"communities,":[11],"understanding":[12,183],"its":[13],"theoretical":[14,182],"foundation":[15],"has":[16],"long":[17],"been":[18],"recognized":[19],"as":[20],"a":[21,33,43,62,76,100,178],"challenging":[22],"problem.":[23],"In":[24],"this":[25,29],"article,":[26],"we":[27,41],"address":[28],"problem":[30],"by":[31,73,157],"providing":[32],"finite-sample":[34,106,146,173,190],"analysis":[35,115,174],"for":[36,148,175],"decentralized":[37,101,158,165],"batch":[38,92,176],"MARL.":[39],"Specifically,":[40],"consider":[42],"type":[44],"of":[45,58,108,123,131,137,184],"mixed":[46],"MARL":[47,84,93,166,186],"setting":[48,80],"with":[49],"both":[50],"cooperative":[51],"and":[52,103,128],"competitive":[53],"agents,":[54],"where":[55],"two":[56],"teams":[57],"agents":[59,68],"compete":[60],"zero-sum":[63],"game":[64],"setting,":[65],"while":[66],"within":[69,125],"each":[70,126],"team":[71],"collaborate":[72],"communicating":[74],"over":[75],"time-varying":[77],"network.":[78],"This":[79,168],"covers":[81],"many":[82],"conventional":[83],"settings":[85],"literature.":[88],"We":[89],"then":[90],"develop":[91],"algorithms":[94,187],"that":[95],"can":[96],"be":[97],"implemented":[98],"fashion,":[102],"quantify":[104],"errors":[107],"estimated":[110],"action-value":[111],"functions.":[112],"Our":[113,141],"error":[114,154],"captures":[116],"how":[117],"function":[119],"class,":[120],"number":[122,130],"samples":[124],"iteration,":[127],"iterations":[132],"determine":[133],"statistical":[135],"accuracy":[136],"proposed":[139],"algorithms.":[140],"results,":[142],"compared":[143],"to":[144],"bounds":[147],"single-agent":[149],"learning,":[151],"involve":[152],"additional":[153],"terms":[155],"caused":[156],"computation,":[159],"which":[160],"is":[161],"inherent":[162],"our":[164],"setting.":[167],"article":[169],"provides":[170],"first":[172],"MARL,":[177],"step":[179],"toward":[180],"rigorous":[181],"general":[185],"regime.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}