{"id":"https://openalex.org/W4380669446","doi":"https://doi.org/10.1145/3578338.3593545","title":"Global Convergence of Localized Policy Iteration in Networked Multi-Agent Reinforcement Learning","display_name":"Global Convergence of Localized Policy Iteration in Networked Multi-Agent Reinforcement Learning","publication_year":2023,"publication_date":"2023-06-13","ids":{"openalex":"https://openalex.org/W4380669446","doi":"https://doi.org/10.1145/3578338.3593545"},"language":"en","primary_location":{"id":"doi:10.1145/3578338.3593545","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3578338.3593545","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Abstract Proceedings of the 2023 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems","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/A5048268146","display_name":"Yizhou Zhang","orcid":"https://orcid.org/0000-0002-5677-4748"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhou Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5677-4748","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060570874","display_name":"Guannan Qu","orcid":"https://orcid.org/0000-0002-5466-3550"},"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":"Guannan Qu","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5466-3550","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396257","display_name":"Pan Xu","orcid":"https://orcid.org/0000-0002-2559-8622"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pan Xu","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"raw_orcid":"https://orcid.org/0000-0002-2559-8622","affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006928264","display_name":"Yiheng Lin","orcid":"https://orcid.org/0000-0001-6524-2877"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiheng Lin","raw_affiliation_strings":["California Institute of Technology, Pasadena, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6524-2877","affiliations":[{"raw_affiliation_string":"California Institute of Technology, Pasadena, CA, USA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058269077","display_name":"Zaiwei Chen","orcid":"https://orcid.org/0000-0001-9915-5595"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zaiwei Chen","raw_affiliation_strings":["California Institute of Technology, Pasadena, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9915-5595","affiliations":[{"raw_affiliation_string":"California Institute of Technology, Pasadena, CA, USA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062565732","display_name":"Adam Wierman","orcid":"https://orcid.org/0000-0002-5923-0199"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Wierman","raw_affiliation_strings":["California Institute of Technology, Pasadena, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5923-0199","affiliations":[{"raw_affiliation_string":"California Institute of Technology, Pasadena, CA, USA","institution_ids":["https://openalex.org/I122411786"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3263,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63514399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"83","last_page":"84"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9988999962806702,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8876651525497437},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.7040947675704956},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6940459609031677},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6316715478897095},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5641142129898071},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.41186562180519104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27728450298309326},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27478599548339844}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8876651525497437},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.7040947675704956},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6940459609031677},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6316715478897095},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5641142129898071},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.41186562180519104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27728450298309326},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27478599548339844},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3578338.3593545","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3578338.3593545","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Abstract Proceedings of the 2023 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1217207130","display_name":null,"funder_award_id":"2154171, 2146814, 2136197, 2106403, 2105648","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2104602264","https://openalex.org/W3004360271","https://openalex.org/W3035141911","https://openalex.org/W3160932951","https://openalex.org/W3208941461","https://openalex.org/W4214759040","https://openalex.org/W4387329047"],"related_works":["https://openalex.org/W4296209631","https://openalex.org/W4306904969","https://openalex.org/W2561617217","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2025378473","https://openalex.org/W2024136090","https://openalex.org/W4391331176"],"abstract_inverted_index":{"We":[0],"study":[1],"a":[2,13,44,53,81],"multi-agent":[3],"reinforcement":[4],"learning":[5],"(MARL)":[6],"problem":[7],"where":[8],"the":[9,19,25,34,75,96,102,109,122],"agents":[10,20,76],"interact":[11],"over":[12],"given":[14],"network.":[15],"The":[16],"goal":[17],"of":[18,27,36,99,124,133],"is":[21,129],"to":[22,39,70,79,101],"cooperatively":[23],"maximize":[24],"average":[26],"their":[28],"entropy-regularized":[29],"long-term":[30],"rewards.":[31],"To":[32],"overcome":[33],"curse":[35],"dimensionality":[37],"and":[38,113],"reduce":[40],"communication,":[41],"we":[42,62,94],"propose":[43],"Localized":[45],"Policy":[46],"Iteration":[47],"(LPI)":[48],"algorithm":[49],"that":[50,87],"provably":[51],"learns":[52],"near-globally-optimal":[54],"policy":[55,82],"using":[56],"only":[57,71],"local":[58],"information.":[59],"In":[60,92],"particular,":[61],"show":[63,95],"that,":[64],"despite":[65],"restricting":[66],"each":[67],"agent's":[68],"attention":[69],"its":[72],"\u03ba-hop":[73],"neighborhood,":[74],"are":[77],"able":[78],"learn":[80],"with":[83],"an":[84,130],"optimality":[85,112],"gap":[86],"decays":[88],"polynomially":[89],"in":[90,116],"\u03ba.":[91,118],"addition,":[93],"finite-sample":[97],"convergence":[98],"LPI":[100],"global":[103],"optimal":[104],"policy,":[105],"which":[106],"explicitly":[107],"captures":[108],"trade-off":[110],"between":[111],"computational":[114],"complexity":[115],"choosing":[117],"Numerical":[119],"simulations":[120],"demonstrate":[121],"effectiveness":[123],"LPI.":[125],"This":[126],"extended":[127],"abstract":[128],"abridged":[131],"version":[132],"[12].":[134]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}