{"id":"https://openalex.org/W1986078872","doi":"https://doi.org/10.1109/tnnls.2013.2270561","title":"Online Selective Kernel-Based Temporal Difference Learning","display_name":"Online Selective Kernel-Based Temporal Difference Learning","publication_year":2013,"publication_date":"2013-11-01","ids":{"openalex":"https://openalex.org/W1986078872","doi":"https://doi.org/10.1109/tnnls.2013.2270561","mag":"1986078872","pmid":"https://pubmed.ncbi.nlm.nih.gov/24805214"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2013.2270561","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2013.2270561","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/A5101574243","display_name":"Xingguo Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingguo Chen","raw_affiliation_strings":["Nanjing University, State Key Laboratory for Novel Software Technology, Nanjing, China","State Key Lab. for Novel Software Tech., Nanjing Univ., Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University, State Key Laboratory for Novel Software Technology, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Lab. for Novel Software Tech., Nanjing Univ., Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074250521","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0002-2488-1813"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Gao","raw_affiliation_strings":["Nanjing University, State Key Laboratory for Novel Software Technology, Nanjing, China","State Key Lab. for Novel Software Tech., Nanjing Univ., Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University, State Key Laboratory for Novel Software Technology, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Lab. for Novel Software Tech., Nanjing Univ., Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100694558","display_name":"Ruili Wang","orcid":"https://orcid.org/0000-0001-7117-2772"},"institutions":[{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Ruili Wang","raw_affiliation_strings":["Massey University, School of Engineering of Advanced Technology, Palmerston North, New Zealand","Sch. of Eng. of Adv. Technol., Massey Univ., Palmerston North, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massey University, School of Engineering of Advanced Technology, Palmerston North, New Zealand","institution_ids":["https://openalex.org/I51158804"]},{"raw_affiliation_string":"Sch. of Eng. of Adv. Technol., Massey Univ., Palmerston North, New Zealand","institution_ids":["https://openalex.org/I51158804"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.842,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.95062862,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"24","issue":"12","first_page":"1944","last_page":"1956"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9973999857902527,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9973999857902527,"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"}},{"id":"https://openalex.org/T12546","display_name":"Smart Parking Systems Research","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9840999841690063,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7093442678451538},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6182919144630432},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5607635974884033},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5055525302886963},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.47466567158699036},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4630105495452881},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4394644796848297},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.43438515067100525},{"id":"https://openalex.org/keywords/variable-kernel-density-estimation","display_name":"Variable kernel density estimation","score":0.41378942131996155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3837425708770752},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33930087089538574},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.1998589038848877}],"concepts":[{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7093442678451538},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6182919144630432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5607635974884033},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5055525302886963},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.47466567158699036},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4630105495452881},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4394644796848297},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.43438515067100525},{"id":"https://openalex.org/C195699287","wikidata":"https://www.wikidata.org/wiki/Q7915722","display_name":"Variable kernel density estimation","level":4,"score":0.41378942131996155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3837425708770752},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33930087089538574},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.1998589038848877},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2013.2270561","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2013.2270561","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:24805214","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24805214","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},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.648.8213","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.648.8213","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.nju.edu.cn/rl/people/chenxg/paper/[2013][chen][tnnls]online selective kernel-based temporal difference learning.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W6614468","https://openalex.org/W86816279","https://openalex.org/W123280120","https://openalex.org/W359568995","https://openalex.org/W1540155273","https://openalex.org/W1550698229","https://openalex.org/W1576452626","https://openalex.org/W1586727544","https://openalex.org/W1592847719","https://openalex.org/W1828381662","https://openalex.org/W1984666348","https://openalex.org/W1986580492","https://openalex.org/W1995688924","https://openalex.org/W2012915481","https://openalex.org/W2046513829","https://openalex.org/W2070676433","https://openalex.org/W2072931156","https://openalex.org/W2075268401","https://openalex.org/W2097381042","https://openalex.org/W2098102888","https://openalex.org/W2100024763","https://openalex.org/W2100128988","https://openalex.org/W2101539915","https://openalex.org/W2104753538","https://openalex.org/W2109102709","https://openalex.org/W2110410904","https://openalex.org/W2115017620","https://openalex.org/W2118556122","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2122021878","https://openalex.org/W2123979492","https://openalex.org/W2124995446","https://openalex.org/W2126025075","https://openalex.org/W2126709692","https://openalex.org/W2128920470","https://openalex.org/W2132333011","https://openalex.org/W2132351269","https://openalex.org/W2132849848","https://openalex.org/W2135293965","https://openalex.org/W2138131694","https://openalex.org/W2140095548","https://openalex.org/W2141007261","https://openalex.org/W2145934551","https://openalex.org/W2150590096","https://openalex.org/W2150841368","https://openalex.org/W2156974606","https://openalex.org/W2159476216","https://openalex.org/W2159543578","https://openalex.org/W2169015875","https://openalex.org/W2171566706","https://openalex.org/W2172968643","https://openalex.org/W2407232290","https://openalex.org/W2964331425","https://openalex.org/W3003446791","https://openalex.org/W4214717370","https://openalex.org/W4245296547","https://openalex.org/W4249441547","https://openalex.org/W6603545158","https://openalex.org/W6632870548","https://openalex.org/W6674600207","https://openalex.org/W6677737365","https://openalex.org/W6679401659","https://openalex.org/W6679599195","https://openalex.org/W6679801795","https://openalex.org/W6681058398","https://openalex.org/W6684975885"],"related_works":["https://openalex.org/W2127229869","https://openalex.org/W2420851703","https://openalex.org/W2095626363","https://openalex.org/W3123056048","https://openalex.org/W1603091392","https://openalex.org/W2165576085","https://openalex.org/W2079825755","https://openalex.org/W2136517333","https://openalex.org/W2179275589","https://openalex.org/W945329738"],"abstract_inverted_index":{"In":[0,94,161,200,219,252],"this":[1],"paper,":[2],"an":[3,207],"online":[4,27,29,48,80,152],"selective":[5,36,55,101,118,127],"kernel-based":[6,37,102,119,128,187],"temporal":[7,137],"difference":[8,138],"(OSKTD)":[9],"learning":[10,22,140],"algorithm":[11,141,158],"is":[12,51,59,78,105,159],"proposed":[13,52,70,106,198],"to":[14,87,90,107,172,206],"deal":[15],"with":[16,64,143,174,231,262],"large":[17],"scale":[18],"and/or":[19],"continuous":[20],"reinforcement":[21],"problems.":[23],"OSKTD":[24,157,204,224,254],"includes":[25],"two":[26,163],"procedures:":[28],"sparsification":[30,42,49,66,71,153,233],"and":[31,167,177,183,190,210,216,244],"parameter":[32],"updating":[33],"for":[34,116],"the":[35,69,73,91,109,113,117,126,136,144,151,156,186,191,194,201,220,241,249,263],"value":[38,103,120,129,188],"function.":[39],"A":[40],"new":[41],"method":[43],"(i.e.,":[44],"a":[45,84,100,236,257],"kernel":[46],"distance-based":[47],"method)":[50],"based":[53,96],"on":[54,97],"ensemble":[56],"learning,":[57],"which":[58],"computationally":[60],"less":[61,227],"complex":[62],"compared":[63,230,261],"other":[65,232],"methods.":[67],"With":[68],"method,":[72],"sparsified":[74,92],"dictionary":[75,115],"of":[76,125,150,196],"samples":[77,111],"constructed":[79],"by":[81,134],"checking":[82],"if":[83],"sample":[85,114],"needs":[86],"be":[88],"added":[89],"dictionary.":[93],"addition,":[95,162,253],"local":[98,238],"validity,":[99],"function":[104,121,130],"select":[108],"best":[110],"from":[112],"approximator.":[122],"The":[123,148],"parameters":[124],"are":[131,170],"iteratively":[132],"updated":[133],"using":[135,185],"(TD)":[139],"combined":[142],"gradient":[145],"descent":[146],"technique.":[147],"complexity":[149],"procedure":[154],"in":[155],"O(n).":[160],"typical":[164],"experiments":[165],"(Maze":[166],"Mountain":[168,221],"Car)":[169],"used":[171],"compare":[173],"both":[175,214],"traditional":[176,215,242],"up-to-date":[178,217,250,264],"O(n)":[179],"algorithms":[180],"(GTD,":[181],"GTD2,":[182],"TDC":[184],"function),":[189],"results":[192],"demonstrate":[193],"effectiveness":[195],"our":[197],"algorithm.":[199],"Maze":[202],"problem,":[203,223],"converges":[205,211,245],"optimal":[208],"policy":[209],"faster":[212,247],"than":[213,240,248],"algorithms.":[218,251,265],"Car":[222],"converges,":[225],"requires":[226],"computation":[228],"time":[229],"methods,":[234],"gets":[235],"better":[237],"optima":[239,260],"algorithms,":[243],"much":[246],"can":[255],"reach":[256],"competitive":[258],"ultimate":[259]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}