{"id":"https://openalex.org/W2044328306","doi":"https://doi.org/10.1109/icassp.2013.6638519","title":"Cooperative off-policy prediction of Markov decision processes in adaptive networks","display_name":"Cooperative off-policy prediction of Markov decision processes in adaptive networks","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2044328306","doi":"https://doi.org/10.1109/icassp.2013.6638519","mag":"2044328306"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/233444","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":false,"raw_author_name":"Sergio Valcarcel Macua","raw_affiliation_strings":["Escuela T\u00e9cnica Superior de Ingenieros de Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","Escuela Tec. Super. de Ing. de Telecomun., Univ. Politec. de Madrid, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Escuela T\u00e9cnica Superior de Ingenieros de Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]},{"raw_affiliation_string":"Escuela Tec. Super. de Ing. de Telecomun., 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"],"raw_orcid":null,"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":["Escuela T\u00e9cnica Superior de Ingenieros de Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","Escuela Tec. Super. de Ing. de Telecomun., Univ. Politec. de Madrid, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Escuela T\u00e9cnica Superior de Ingenieros de Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]},{"raw_affiliation_string":"Escuela Tec. Super. de Ing. de Telecomun., 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"],"raw_orcid":null,"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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4539","last_page":"4543"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T12592","display_name":"Opinion Dynamics and Social Influence","score":0.9901999831199646,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7959370613098145},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7717826962471008},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7018330097198486},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6503781080245972},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6377056837081909},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6143526434898376},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5183899998664856},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4655291438102722},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.44911420345306396},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.43671682476997375},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4195847809314728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4194675087928772},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3872453570365906},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3204650282859802},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2668299674987793},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1521541178226471},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1422017514705658}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7959370613098145},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7717826962471008},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7018330097198486},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6503781080245972},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6377056837081909},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6143526434898376},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5183899998664856},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4655291438102722},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.44911420345306396},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.43671682476997375},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4195847809314728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4194675087928772},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3872453570365906},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3204650282859802},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2668299674987793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1521541178226471},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1422017514705658},{"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/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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2013.6638519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1013.568","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1013.568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Sergio_Valcarcel_Macua/publication/251229584_Cooperative_Off-Policy_Prediction_of_Markov_Decision_Processes_in_Adaptive_Networks/links/0deec51eead901cf5d000000.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:233444","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/233444","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"},{"id":"pmh:oai:oa.upm.es:28941","is_oa":true,"landing_page_url":"http://oa.upm.es/28941/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402421","display_name":"Archivo Digital UPM (Universidad Polit\u00e9cnica de Madrid)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I88060688","host_organization_name":"Universidad Polit\u00e9cnica de Madrid","host_organization_lineage":["https://openalex.org/I88060688"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) | IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) | 26/05/2013 - 31/05/2013 | Vancouver, Canada","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:233444","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/233444","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":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1964135056","https://openalex.org/W1980241579","https://openalex.org/W2027648864","https://openalex.org/W2029080014","https://openalex.org/W2075268401","https://openalex.org/W2103220021","https://openalex.org/W2104753538","https://openalex.org/W2108596215","https://openalex.org/W2119567691","https://openalex.org/W2121820607","https://openalex.org/W2132622533","https://openalex.org/W2134042548","https://openalex.org/W2153039919","https://openalex.org/W2165905123","https://openalex.org/W2334782222","https://openalex.org/W2570416447","https://openalex.org/W2610805269","https://openalex.org/W2951143668","https://openalex.org/W2963157432","https://openalex.org/W4239240501","https://openalex.org/W4298760293","https://openalex.org/W6675243623","https://openalex.org/W6676024505","https://openalex.org/W6679365036","https://openalex.org/W6683221847","https://openalex.org/W6684139056","https://openalex.org/W6684488654","https://openalex.org/W7065010408"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4225269853"],"abstract_inverted_index":{"We":[0,39,76],"apply":[1],"diffusion":[2],"strategies":[3],"to":[4,21,31],"propose":[5],"a":[6,15,41,73],"cooperative":[7],"reinforcement":[8],"learning":[9],"algorithm,":[10],"in":[11,14,35,52,63,69,81],"which":[12],"agents":[13,92],"network":[16],"communicate":[17],"with":[18],"their":[19,25],"neighbors":[20],"improve":[22],"predictions":[23],"about":[24],"environment.":[26],"The":[27,48],"algorithm":[28],"is":[29,67,83,93],"suitable":[30],"learn":[32],"off-policy":[33],"even":[34],"large":[36],"state":[37],"spaces.":[38],"provide":[40],"mean-square-error":[42],"performance":[43,82],"analysis":[44],"under":[45,99],"constant":[46],"step-sizes.":[47],"gain":[49],"of":[50,55,72,90],"cooperation":[51],"the":[53,64,70,79,87,91,96],"form":[54],"more":[56],"stability":[57],"and":[58,61],"less":[59],"bias":[60],"variance":[62],"prediction":[65],"error,":[66],"illustrated":[68],"context":[71],"classical":[74],"model.":[75],"show":[77],"that":[78],"improvement":[80],"especially":[84],"significant":[85],"when":[86],"behavior":[88],"policy":[89,98],"different":[94],"from":[95],"target":[97],"evaluation.":[100]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}