{"id":"https://openalex.org/W2088542838","doi":"https://doi.org/10.1109/tnnls.2015.2424233","title":"Kernel-Based Least Squares Temporal Difference With Gradient Correction","display_name":"Kernel-Based Least Squares Temporal Difference With Gradient Correction","publication_year":2015,"publication_date":"2015-05-01","ids":{"openalex":"https://openalex.org/W2088542838","doi":"https://doi.org/10.1109/tnnls.2015.2424233","mag":"2088542838","pmid":"https://pubmed.ncbi.nlm.nih.gov/25955853"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2015.2424233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2015.2424233","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/A5102884128","display_name":"Tianheng Song","orcid":"https://orcid.org/0000-0001-8275-5535"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianheng Song","raw_affiliation_strings":["Institute of Automation, Beijing University of Chemical Technology, Beijing, China","[Institute of Automation Beijing University of Chemical Technology, Beijing, China]"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Beijing University of Chemical Technology, Beijing, China","institution_ids":["https://openalex.org/I75390827","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"[Institute of Automation Beijing University of Chemical Technology, Beijing, China]","institution_ids":["https://openalex.org/I75390827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064212043","display_name":"Dazi Li","orcid":"https://orcid.org/0000-0003-1610-6558"},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dazi Li","raw_affiliation_strings":["Institute of Automation, Beijing University of Chemical Technology, Beijing, China","[Institute of Automation Beijing University of Chemical Technology, Beijing, China]"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Beijing University of Chemical Technology, Beijing, China","institution_ids":["https://openalex.org/I75390827","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"[Institute of Automation Beijing University of Chemical Technology, Beijing, China]","institution_ids":["https://openalex.org/I75390827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100889546","display_name":"Liulin Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liulin Cao","raw_affiliation_strings":["Institute of Automation, Beijing University of Chemical Technology, Beijing, China","[Institute of Automation Beijing University of Chemical Technology, Beijing, China]"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Beijing University of Chemical Technology, Beijing, China","institution_ids":["https://openalex.org/I75390827","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"[Institute of Automation Beijing University of Chemical Technology, Beijing, China]","institution_ids":["https://openalex.org/I75390827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013008417","display_name":"Kotaro Hirasawa","orcid":null},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kotaro Hirasawa","raw_affiliation_strings":["Institute of Automation, Beijing University of Chemical Technology, Beijing, China","[Institute of Automation Beijing University of Chemical Technology, Beijing, China]"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Beijing University of Chemical Technology, Beijing, China","institution_ids":["https://openalex.org/I75390827","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"[Institute of Automation Beijing University of Chemical Technology, Beijing, China]","institution_ids":["https://openalex.org/I75390827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102884128"],"corresponding_institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I75390827"],"apc_list":null,"apc_paid":null,"fwci":3.2489,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.91015923,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"27","issue":"4","first_page":"771","last_page":"782"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9927999973297119,"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"}},"topics":[{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9927999973297119,"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"}},{"id":"https://openalex.org/T11749","display_name":"Iterative Learning Control Systems","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11236","display_name":"Control Systems and Identification","score":0.9850000143051147,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/robustness","display_name":"Robustness (evolution)","score":0.7210900187492371},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.692872166633606},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6143953800201416},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5930358171463013},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.506196916103363},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.45820972323417664},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43551957607269287},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4301770329475403},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34823077917099},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3106306791305542}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7210900187492371},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.692872166633606},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6143953800201416},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5930358171463013},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.506196916103363},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.45820972323417664},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43551957607269287},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4301770329475403},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34823077917099},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3106306791305542},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2015.2424233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2015.2424233","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:25955853","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25955853","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":[],"awards":[{"id":"https://openalex.org/G5663249744","display_name":null,"funder_award_id":"61473024","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W13294968","https://openalex.org/W1646707810","https://openalex.org/W1986078872","https://openalex.org/W2011197824","https://openalex.org/W2012915481","https://openalex.org/W2046513829","https://openalex.org/W2050522395","https://openalex.org/W2053449276","https://openalex.org/W2069017697","https://openalex.org/W2071820974","https://openalex.org/W2072931156","https://openalex.org/W2075268401","https://openalex.org/W2098432798","https://openalex.org/W2113455337","https://openalex.org/W2114865067","https://openalex.org/W2118556122","https://openalex.org/W2126410641","https://openalex.org/W2126709692","https://openalex.org/W2129564505","https://openalex.org/W2132351269","https://openalex.org/W2132849848","https://openalex.org/W2134042548","https://openalex.org/W2139320579","https://openalex.org/W2139418546","https://openalex.org/W2147839652","https://openalex.org/W2153290280","https://openalex.org/W2156974606","https://openalex.org/W2165905123","https://openalex.org/W2586680856","https://openalex.org/W3035712376","https://openalex.org/W3144619878","https://openalex.org/W4214717370","https://openalex.org/W4236439427","https://openalex.org/W4285719527","https://openalex.org/W4299401133","https://openalex.org/W6600556750","https://openalex.org/W6676641278","https://openalex.org/W6677089629","https://openalex.org/W6678750431","https://openalex.org/W6679599195","https://openalex.org/W6684488654","https://openalex.org/W7065010408"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W2768629321","https://openalex.org/W4384574988","https://openalex.org/W2130711276","https://openalex.org/W4321463377","https://openalex.org/W4308828368","https://openalex.org/W1528400370"],"abstract_inverted_index":{"A":[0],"least":[1,51],"squares":[2,52],"temporal":[3],"difference":[4],"with":[5,134],"gradient":[6],"correction":[7],"(LS-TDC)":[8],"algorithm":[9],"and":[10,65,111,117,126,145,150,163],"its":[11],"kernel-based":[12,14],"version":[13],"LS-TDC":[15,27,45,116,144],"(KLS-TDC)":[16],"are":[17,119],"proposed":[18],"as":[19,132],"policy":[20,96],"evaluation":[21],"algorithms":[22],"for":[23,155],"reinforcement":[24],"learning":[25,107,128],"(RL).":[26],"is":[28,54,74,87,102],"derived":[29,37],"from":[30],"the":[31,40,58,62,71],"TDC":[32,36,64],"algorithm.":[33],"Attributed":[34],"to":[35,56,89,104,166],"by":[38,100],"minimizing":[39],"mean-square":[41],"projected":[42],"Bellman":[43],"error,":[44],"has":[46],"better":[47,148],"convergence":[48,110,151],"performance.":[49],"The":[50,82,109],"technique":[53],"used":[55],"omit":[57],"size-step":[59],"tuning":[60],"of":[61,114,137,160],"original":[63],"enhance":[66],"robustness.":[67],"For":[68],"KLS-TDC,":[69],"since":[70],"kernel":[72,91],"method":[73],"used,":[75],"feature":[76],"vectors":[77],"can":[78],"be":[79],"selected":[80],"automatically.":[81],"approximate":[83],"linear":[84],"dependence":[85],"analysis":[86],"performed":[88],"realize":[90],"sparsification.":[92],"In":[93],"addition,":[94],"a":[95,135],"iteration":[97],"strategy":[98],"motivated":[99],"KLS-TDC":[101,118,146],"constructed":[103],"solve":[105],"control":[106,127],"problems.":[108,129],"parameter":[112,161],"sensitivities":[113],"both":[115,143],"tested":[120],"through":[121],"on-policy":[122],"learning,":[123,125],"off-policy":[124],"Experimental":[130],"results,":[131],"compared":[133],"series":[136],"corresponding":[138],"RL":[139],"algorithms,":[140],"demonstrate":[141],"that":[142],"have":[147],"approximation":[149],"performance,":[152],"higher":[153],"efficiency":[154],"sample":[156],"usage,":[157],"smaller":[158],"burden":[159],"tuning,":[162],"less":[164],"sensitivity":[165],"parameters.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}