{"id":"https://openalex.org/W4402569979","doi":"https://doi.org/10.1109/tnnls.2024.3453036","title":"Kernel-Based Decentralized Policy Evaluation for Reinforcement Learning","display_name":"Kernel-Based Decentralized Policy Evaluation for Reinforcement Learning","publication_year":2024,"publication_date":"2024-09-17","ids":{"openalex":"https://openalex.org/W4402569979","doi":"https://doi.org/10.1109/tnnls.2024.3453036","pmid":"https://pubmed.ncbi.nlm.nih.gov/39288039"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3453036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3453036","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5115593395","display_name":"Jiamin Liu","orcid":"https://orcid.org/0000-0003-0118-4852"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiamin Liu","raw_affiliation_strings":["School of Mathematics and Physics, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Mathematics and Physics, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069315147","display_name":"Heng Lian","orcid":"https://orcid.org/0000-0002-6008-6614"},"institutions":[{"id":"https://openalex.org/I4210105229","display_name":"City University of Hong Kong, Shenzhen Research Institute","ror":"https://ror.org/00xc0ma20","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210105229"]},{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Heng Lian","raw_affiliation_strings":["City University of Hong Kong Shenzhen Research Institute, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong Shenzhen Research Institute, Shenzhen, China","institution_ids":["https://openalex.org/I168719708","https://openalex.org/I4210105229"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5115593395"],"corresponding_institution_ids":["https://openalex.org/I92403157"],"apc_list":null,"apc_paid":null,"fwci":0.8836,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72792859,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"36","issue":"6","first_page":"10371","last_page":"10380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9919000267982483,"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"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9919000267982483,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11520","display_name":"Advanced Thermodynamics and Statistical Mechanics","score":0.9839000105857849,"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/reproducing-kernel-hilbert-space","display_name":"Reproducing kernel Hilbert space","score":0.8583667278289795},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8252664804458618},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6532068252563477},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.6336671113967896},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6078864336013794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.578995943069458},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5511445999145508},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5191137790679932},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.49840664863586426},{"id":"https://openalex.org/keywords/nonparametric-regression","display_name":"Nonparametric regression","score":0.4897937774658203},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.48693931102752686},{"id":"https://openalex.org/keywords/hilbert-space","display_name":"Hilbert space","score":0.4710167646408081},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.4284512996673584},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36593207716941833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.344191312789917},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22701549530029297},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14169487357139587},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.10982492566108704}],"concepts":[{"id":"https://openalex.org/C80884492","wikidata":"https://www.wikidata.org/wiki/Q3345678","display_name":"Reproducing kernel Hilbert space","level":3,"score":0.8583667278289795},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8252664804458618},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6532068252563477},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.6336671113967896},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6078864336013794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.578995943069458},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5511445999145508},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5191137790679932},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.49840664863586426},{"id":"https://openalex.org/C74127309","wikidata":"https://www.wikidata.org/wiki/Q3455886","display_name":"Nonparametric regression","level":3,"score":0.4897937774658203},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.48693931102752686},{"id":"https://openalex.org/C62799726","wikidata":"https://www.wikidata.org/wiki/Q190056","display_name":"Hilbert space","level":2,"score":0.4710167646408081},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.4284512996673584},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36593207716941833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.344191312789917},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22701549530029297},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14169487357139587},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.10982492566108704},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3453036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3453036","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:39288039","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39288039","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G4596100614","display_name":null,"funder_award_id":"12371297","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1616857247","https://openalex.org/W1986280275","https://openalex.org/W2137435346","https://openalex.org/W2404399993","https://openalex.org/W2580909119","https://openalex.org/W2837605352","https://openalex.org/W2963616027","https://openalex.org/W2963940890","https://openalex.org/W2964123095","https://openalex.org/W3009640417","https://openalex.org/W3020125231","https://openalex.org/W3041202696","https://openalex.org/W3174733757","https://openalex.org/W3187550742","https://openalex.org/W3200466256","https://openalex.org/W3207876914","https://openalex.org/W4282930937","https://openalex.org/W4283699829","https://openalex.org/W4293872189","https://openalex.org/W4297964528","https://openalex.org/W4298876635","https://openalex.org/W4307230233","https://openalex.org/W4378805020","https://openalex.org/W4397026139","https://openalex.org/W6639039794","https://openalex.org/W6676930901","https://openalex.org/W6682074005","https://openalex.org/W6683673261","https://openalex.org/W6736209634","https://openalex.org/W6738250615","https://openalex.org/W6748599296","https://openalex.org/W6752725515","https://openalex.org/W6758846586","https://openalex.org/W6762191990","https://openalex.org/W6763317420","https://openalex.org/W6766156165","https://openalex.org/W6774159089","https://openalex.org/W6780179245"],"related_works":["https://openalex.org/W1541412963","https://openalex.org/W2184572292","https://openalex.org/W1509119367","https://openalex.org/W4321367829","https://openalex.org/W2041704562","https://openalex.org/W4309301076","https://openalex.org/W2288767749","https://openalex.org/W4313160815","https://openalex.org/W2181913714","https://openalex.org/W2949120947"],"abstract_inverted_index":{"We":[0,72,98],"investigate":[1],"the":[2,21,79,86,100,104],"decentralized":[3,95],"nonparametric":[4,96],"policy":[5],"evaluation":[6],"problem":[7],"within":[8,46,92],"reinforcement":[9],"learning":[10],"(RL),":[11],"focusing":[12],"on":[13,35],"scenarios":[14],"where":[15],"multiple":[16],"agents":[17],"collaborate":[18],"to":[19,64,77,103],"learn":[20],"state-value":[22],"function":[23,83],"using":[24],"sampled":[25],"state":[26],"transitions":[27],"and":[28,56],"privately":[29],"observed":[30],"rewards.":[31],"Our":[32],"approach":[33],"centers":[34],"a":[36,47,69,93],"regression-based":[37,101],"multistage":[38],"iteration":[39],"technique":[40],"employing":[41],"infinite-dimensional":[42],"gradient":[43],"descent":[44],"(GD)":[45],"reproducing":[48],"kernel":[49,105],"Hilbert":[50],"space":[51,67],"(RKHS).":[52],"To":[53],"make":[54],"computation":[55],"communication":[57],"more":[58],"feasible,":[59],"we":[60],"employ":[61],"Nystr\u00f6m":[62],"approximation":[63],"project":[65],"this":[66],"into":[68],"finite-dimensional":[70],"one.":[71],"establish":[73],"statistical":[74],"error":[75],"bounds":[76],"describe":[78],"convergence":[80],"of":[81,89],"value":[82],"estimation,":[84],"marking":[85],"first":[87],"instance":[88],"such":[90],"analysis":[91],"fully":[94],"framework.":[97],"compare":[99],"method":[102,109],"temporal":[106],"difference":[107],"(TD)":[108],"in":[110],"some":[111],"numerical":[112],"studies.":[113]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}