{"id":"https://openalex.org/W2126059761","doi":"https://doi.org/10.1109/cdc.2011.6160491","title":"Policy iteration algorithm for distributed networks and graphical games","display_name":"Policy iteration algorithm for distributed networks and graphical games","publication_year":2011,"publication_date":"2011-12-01","ids":{"openalex":"https://openalex.org/W2126059761","doi":"https://doi.org/10.1109/cdc.2011.6160491","mag":"2126059761"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2011.6160491","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2011.6160491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Conference on Decision and Control and European Control Conference","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/A5040301558","display_name":"Kyriakos G. Vamvoudakis","orcid":"https://orcid.org/0000-0003-1978-4848"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kyriakos G. Vamvoudakis","raw_affiliation_strings":["Automation and Robotics Research Institute, University of Texas, Arlington, Fort Worth, TX, USA","Automation and Robotics Research Institute, University of Texas at Arlington, 7300 Jack Newell Blvd. S. Fort Worth, 76118 USA"],"affiliations":[{"raw_affiliation_string":"Automation and Robotics Research Institute, University of Texas, Arlington, Fort Worth, TX, USA","institution_ids":["https://openalex.org/I4210116723"]},{"raw_affiliation_string":"Automation and Robotics Research Institute, University of Texas at Arlington, 7300 Jack Newell Blvd. S. Fort Worth, 76118 USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"F. L. Lewis","raw_affiliation_strings":["Automation and Robotics Research Institute, University of Texas, Arlington, Fort Worth, TX, USA","Automation and Robotics Research Institute, University of Texas at Arlington, 7300 Jack Newell Blvd. S. Fort Worth, 76118 USA"],"affiliations":[{"raw_affiliation_string":"Automation and Robotics Research Institute, University of Texas, Arlington, Fort Worth, TX, USA","institution_ids":["https://openalex.org/I4210116723"]},{"raw_affiliation_string":"Automation and Robotics Research Institute, University of Texas at Arlington, 7300 Jack Newell Blvd. S. Fort Worth, 76118 USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5040301558"],"corresponding_institution_ids":["https://openalex.org/I189196454","https://openalex.org/I4210116723"],"apc_list":null,"apc_paid":null,"fwci":2.1005,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88047697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"49","issue":null,"first_page":"128","last_page":"135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7117276191711426},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6590805649757385},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6062865257263184},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6026111841201782},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.5948730707168579},{"id":"https://openalex.org/keywords/graphical-model","display_name":"Graphical model","score":0.5441185235977173},{"id":"https://openalex.org/keywords/distributed-algorithm","display_name":"Distributed algorithm","score":0.5250025987625122},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5222026705741882},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.49811410903930664},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.4292653501033783},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3750763237476349},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.365065336227417},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22194015979766846},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.20843952894210815},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1817590594291687},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.09060239791870117}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7117276191711426},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6590805649757385},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6062865257263184},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6026111841201782},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.5948730707168579},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.5441185235977173},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.5250025987625122},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5222026705741882},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.49811410903930664},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.4292653501033783},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3750763237476349},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.365065336227417},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22194015979766846},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.20843952894210815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1817590594291687},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.09060239791870117},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2011.6160491","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2011.6160491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Conference on Decision and Control and European Control Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1547358136","https://openalex.org/W1602326725","https://openalex.org/W1630241696","https://openalex.org/W1973039793","https://openalex.org/W1983523797","https://openalex.org/W1990199628","https://openalex.org/W2005229381","https://openalex.org/W2019338681","https://openalex.org/W2024303516","https://openalex.org/W2065632630","https://openalex.org/W2072718225","https://openalex.org/W2075489015","https://openalex.org/W2095590702","https://openalex.org/W2099175737","https://openalex.org/W2099618002","https://openalex.org/W2107396783","https://openalex.org/W2113127719","https://openalex.org/W2115159869","https://openalex.org/W2117717397","https://openalex.org/W2121863487","https://openalex.org/W2124152208","https://openalex.org/W2125256511","https://openalex.org/W2131363581","https://openalex.org/W2146804198","https://openalex.org/W2146890818","https://openalex.org/W2147539438","https://openalex.org/W2160135758","https://openalex.org/W2160643434","https://openalex.org/W2165744313","https://openalex.org/W2335728298","https://openalex.org/W2400458653","https://openalex.org/W3121926921","https://openalex.org/W3213472335","https://openalex.org/W4214717370","https://openalex.org/W4231011685","https://openalex.org/W4252284432","https://openalex.org/W4302033101","https://openalex.org/W6677827922","https://openalex.org/W6683733446","https://openalex.org/W6804409665"],"related_works":["https://openalex.org/W4312141693","https://openalex.org/W1536009559","https://openalex.org/W2103821767","https://openalex.org/W1969185016","https://openalex.org/W2037619003","https://openalex.org/W2111030377","https://openalex.org/W1965856819","https://openalex.org/W2914286174","https://openalex.org/W2316903755","https://openalex.org/W4289542303"],"abstract_inverted_index":{"This":[0,55,121],"paper":[1],"brings":[2],"together":[3],"cooperative":[4,48],"control,":[5],"reinforcement":[6],"learning,":[7],"and":[8,33,73,113],"game":[9],"theory":[10],"to":[11,58,74,126],"present":[12],"a":[13,47],"multi-agent":[14],"distributed":[15],"formulation":[16],"for":[17,27,36,52,129],"graphical":[18,23,53,135],"games.":[19,54],"The":[20],"notion":[21],"of":[22,65,92,100,102,105,134],"games":[24,136],"is":[25,86,95],"developed":[26],"dynamical":[28],"systems,":[29],"where":[30],"the":[31,59,63,75,90,98,103,109,118],"dynamics":[32],"performance":[34,119],"indices":[35],"each":[37,66],"node":[38],"depend":[39],"only":[40],"on":[41,97],"local":[42],"neighbor":[43],"information.":[44],"We":[45],"propose":[46],"policy":[49],"iteration":[50],"algorithm":[51,56,94],"converges":[57],"best":[60],"response":[61],"when":[62,78],"neighbors":[64,104],"agent":[67],"do":[68],"not":[69],"update":[70,81],"their":[71,82],"policies":[72,83],"Nash":[76],"equilibrium":[77],"all":[79],"agents":[80],"simultaneously.":[84],"It":[85],"also":[87],"shown":[88],"that":[89],"convergence":[91,101],"this":[93],"based":[96],"speed":[99],"every":[106],"player":[107],"in":[108,117,137],"graph,":[110],"graph":[111],"topology,":[112],"user":[114],"defined":[115],"matrices":[116],"index.":[120],"framework":[122],"will":[123],"be":[124],"used":[125],"develop":[127],"methods":[128],"online":[130],"adaptive":[131],"learning":[132],"solutions":[133],"real":[138],"time.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}