{"id":"https://openalex.org/W2144672231","doi":"https://doi.org/10.1109/tac.2014.2368731","title":"Distributed Policy Evaluation Under Multiple Behavior Strategies","display_name":"Distributed Policy Evaluation Under Multiple Behavior Strategies","publication_year":2014,"publication_date":"2014-11-07","ids":{"openalex":"https://openalex.org/W2144672231","doi":"https://doi.org/10.1109/tac.2014.2368731","mag":"2144672231"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2014.2368731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2014.2368731","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":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/233465","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031787043","display_name":"Sergio Valc\u00e1rcel Macua","orcid":"https://orcid.org/0000-0003-4551-5625"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Sergio Valcarcel Macua","raw_affiliation_strings":["Department of Signals, Systems and Radiocommunications, Escuela T\u00e9cnica Superior de Ingenieros de Telecomunicai\u00f3n, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","Dept. of Signals, Syst. & Radiocommun., Univ. Politec. de Madrid, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Signals, Systems and Radiocommunications, Escuela T\u00e9cnica Superior de Ingenieros de Telecomunicai\u00f3n, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]},{"raw_affiliation_string":"Dept. of Signals, Syst. & Radiocommun., Univ. Politec. de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088339142","display_name":"Jianshu Chen","orcid":"https://orcid.org/0000-0001-8216-2756"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianshu Chen","raw_affiliation_strings":["Department of Electrical Engineering, University of California, Los Angeles, CA, USA","Dept. of Electr. Eng., Univ. of California Los Angeles, Los Angeles, CA, , USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Univ. of California Los Angeles, Los Angeles, CA, , USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008317106","display_name":"Santiago Zazo","orcid":"https://orcid.org/0000-0001-9073-7927"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Santiago Zazo","raw_affiliation_strings":["Department of Signals, Systems and Radiocommunications, Escuela T\u00e9cnica Superior de Ingenieros de Telecomunicai\u00f3n, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","Dept. of Signals, Syst. & Radiocommun., Univ. Politec. de Madrid, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Signals, Systems and Radiocommunications, Escuela T\u00e9cnica Superior de Ingenieros de Telecomunicai\u00f3n, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]},{"raw_affiliation_string":"Dept. of Signals, Syst. & Radiocommun., Univ. Politec. de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091103447","display_name":"Ali H. Sayed","orcid":"https://orcid.org/0000-0002-5125-5519"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali H. Sayed","raw_affiliation_strings":["Department of Electrical Engineering, University of California, Los Angeles, CA, USA","Dept. of Electr. Eng., Univ. of California Los Angeles, Los Angeles, CA, , USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Univ. of California Los Angeles, Los Angeles, CA, , USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031787043"],"corresponding_institution_ids":["https://openalex.org/I88060688"],"apc_list":null,"apc_paid":null,"fwci":4.1377,"has_fulltext":false,"cited_by_count":95,"citation_normalized_percentile":{"value":0.94633947,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"60","issue":"5","first_page":"1260","last_page":"1274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9973999857902527,"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/T12592","display_name":"Opinion Dynamics and Social Influence","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7737034559249878},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7730144262313843},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6665415167808533},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5795937776565552},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5446720123291016},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5423756837844849},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.4236820340156555},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4168365001678467},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3379785418510437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3175293803215027},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.25565099716186523},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19036853313446045},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12414473295211792}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7737034559249878},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7730144262313843},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6665415167808533},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5795937776565552},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5446720123291016},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5423756837844849},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.4236820340156555},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4168365001678467},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3379785418510437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3175293803215027},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25565099716186523},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19036853313446045},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12414473295211792},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tac.2014.2368731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2014.2368731","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:infoscience.epfl.ch:233465","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/233465","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:233465","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/233465","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W5385147","https://openalex.org/W1488636191","https://openalex.org/W1568288633","https://openalex.org/W1600293573","https://openalex.org/W1646707810","https://openalex.org/W1861901279","https://openalex.org/W1863534978","https://openalex.org/W1918371733","https://openalex.org/W1971048324","https://openalex.org/W1980241579","https://openalex.org/W1998172110","https://openalex.org/W2007208291","https://openalex.org/W2024307985","https://openalex.org/W2027481851","https://openalex.org/W2027648864","https://openalex.org/W2029080014","https://openalex.org/W2042664989","https://openalex.org/W2044212084","https://openalex.org/W2044328306","https://openalex.org/W2056182476","https://openalex.org/W2071983464","https://openalex.org/W2072054128","https://openalex.org/W2075268401","https://openalex.org/W2086502731","https://openalex.org/W2098432798","https://openalex.org/W2103220021","https://openalex.org/W2107396783","https://openalex.org/W2108596215","https://openalex.org/W2118776392","https://openalex.org/W2119567691","https://openalex.org/W2119596571","https://openalex.org/W2121820607","https://openalex.org/W2121863487","https://openalex.org/W2122372591","https://openalex.org/W2123183226","https://openalex.org/W2123979492","https://openalex.org/W2132622533","https://openalex.org/W2139418546","https://openalex.org/W2141870784","https://openalex.org/W2145574455","https://openalex.org/W2153267861","https://openalex.org/W2153368486","https://openalex.org/W2154834860","https://openalex.org/W2159752377","https://openalex.org/W2165469059","https://openalex.org/W2165905123","https://openalex.org/W2275663169","https://openalex.org/W2295500362","https://openalex.org/W2296319761","https://openalex.org/W2334782222","https://openalex.org/W2386509573","https://openalex.org/W2471517265","https://openalex.org/W2610805269","https://openalex.org/W2610857016","https://openalex.org/W2951143668","https://openalex.org/W2963157432","https://openalex.org/W3016074254","https://openalex.org/W3142298378","https://openalex.org/W4214717370","https://openalex.org/W4238850922","https://openalex.org/W4239240501","https://openalex.org/W4250589301","https://openalex.org/W4301121837","https://openalex.org/W6628981685","https://openalex.org/W6639355299","https://openalex.org/W6645183936","https://openalex.org/W6661712029","https://openalex.org/W6669700244","https://openalex.org/W6675243623","https://openalex.org/W6676024505","https://openalex.org/W6678257681","https://openalex.org/W6679365036","https://openalex.org/W6684488654"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W4206669594","https://openalex.org/W2959276766","https://openalex.org/W2031695474","https://openalex.org/W2100179986","https://openalex.org/W1544566217","https://openalex.org/W2182183508","https://openalex.org/W2952905979","https://openalex.org/W4294555834","https://openalex.org/W2618318883"],"abstract_inverted_index":{"We":[0,74],"apply":[1],"diffusion":[2],"strategies":[3],"to":[4,24,36,47,130,152],"develop":[5],"a":[6,16,48,76,98,154],"fully-distributed":[7],"cooperative":[8],"reinforcement":[9],"learning":[10,93],"algorithm":[11,31],"in":[12,15,67],"which":[13,87],"agents":[14,42,106,141],"network":[17,90,127],"communicate":[18],"only":[19],"with":[20,64,91],"their":[21,28],"immediate":[22],"neighbors":[23],"improve":[25],"predictions":[26],"about":[27],"environment.":[29],"The":[30,58,95],"can":[32,43,107,142],"also":[33],"be":[34],"applied":[35],"off-policy":[37],"learning,":[38],"meaning":[39],"that":[40],"the":[41,45,52,89,104,109,120,126,132,139,145,158],"predict":[44],"response":[46],"behavior":[49,147],"different":[50],"from":[51,101],"actual":[53],"policies":[54,148],"they":[55],"are":[56],"following.":[57],"proposed":[59],"distributed":[60],"strategy":[61],"is":[62,128],"efficient,":[63],"linear":[65],"complexity":[66],"both":[68],"computation":[69],"time":[70],"and":[71,80,114,117],"memory":[72],"footprint.":[73],"provide":[75],"mean-square-error":[77],"performance":[78],"analysis":[79],"establish":[81],"convergence":[82],"under":[83],"constant":[84],"step-size":[85],"updates,":[86],"endow":[88],"continuous":[92],"capabilities.":[94],"results":[96],"show":[97],"clear":[99],"gain":[100],"cooperation:":[102],"when":[103,136,144],"individual":[105,140,146],"estimate":[108],"solution,":[110],"cooperation":[111],"increases":[112],"stability":[113],"reduces":[115],"bias":[116],"variance":[118],"of":[119,138,157],"prediction":[121],"error;":[122],"but,":[123],"more":[124],"importantly,":[125],"able":[129],"approach":[131],"optimal":[133],"solution":[134],"even":[135],"none":[137],"(e.g.,":[143],"restrict":[149],"each":[150],"agent":[151],"sample":[153],"small":[155],"portion":[156],"state":[159],"space).":[160]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}