{"id":"https://openalex.org/W2755382219","doi":"https://doi.org/10.2298/csis170107029z","title":"A kernel based true online Sarsa(\u03bb) for continuous space control problems","display_name":"A kernel based true online Sarsa(\u03bb) for continuous space control problems","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2755382219","doi":"https://doi.org/10.2298/csis170107029z","mag":"2755382219"},"language":"en","primary_location":{"id":"doi:10.2298/csis170107029z","is_oa":true,"landing_page_url":"https://doi.org/10.2298/csis170107029z","pdf_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02141700029Z","source":{"id":"https://openalex.org/S206939107","display_name":"Computer Science and Information Systems","issn_l":"1820-0214","issn":["1820-0214","2406-1018"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321031","host_organization_name":"ComSIS Consortium","host_organization_lineage":["https://openalex.org/P4310321031"],"host_organization_lineage_names":["ComSIS Consortium"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science and Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02141700029Z","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074124642","display_name":"Fei Zhu","orcid":"https://orcid.org/0000-0002-2226-2859"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Zhu","raw_affiliation_strings":["Soochow University, School of Computer Science and Technology, Suzhou, Jiangsu, China + Soochow University, Provincial Key Laboratory for Computer Information Processing Technology, Suzhou, Jiangsu, China","School of Computer Science and Technology, Soochow University Shizi Street No.1 158 box, 215006, Suzhou, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University, School of Computer Science and Technology, Suzhou, Jiangsu, China + Soochow University, Provincial Key Laboratory for Computer Information Processing Technology, Suzhou, Jiangsu, China","institution_ids":["https://openalex.org/I3923682"]},{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University Shizi Street No.1 158 box, 215006, Suzhou, Jiangsu, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109301828","display_name":"Haijun Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haijun Zhu","raw_affiliation_strings":["Soochow University, School of Computer Science and Technology, Suzhou, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University, School of Computer Science and Technology, Suzhou, Jiangsu, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026708634","display_name":"Yuchen Fu","orcid":"https://orcid.org/0000-0002-7743-3635"},"institutions":[{"id":"https://openalex.org/I21741975","display_name":"Suzhou University of Technology","ror":"https://ror.org/05g6ben79","country_code":"CN","type":"education","lineage":["https://openalex.org/I21741975"]},{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Fu","raw_affiliation_strings":["School of Computer Science and Engineering, Changshu Institute of Technology, China","School of Computer Science and Technology, Soochow University Shizi Street No.1 158 box, 215006, Suzhou, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Changshu Institute of Technology, China","institution_ids":["https://openalex.org/I21741975"]},{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University Shizi Street No.1 158 box, 215006, Suzhou, Jiangsu, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044691927","display_name":"Donghuo Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donghuo Chen","raw_affiliation_strings":["Soochow University, School of Computer Science and Technology, Suzhou, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University, School of Computer Science and Technology, Suzhou, Jiangsu, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049334056","display_name":"Xiaoke Zhou","orcid":"https://orcid.org/0000-0002-1149-729X"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]},{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN","ES"],"is_corresponding":false,"raw_author_name":"Xiaoke Zhou","raw_affiliation_strings":["University of Basque Country, Spain","School of Computer Science and Technology, Soochow University Shizi Street No.1 158 box, 215006, Suzhou, Jiangsu, China","University of Basque Country, Spanish"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Basque Country, Spain","institution_ids":["https://openalex.org/I169108374"]},{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University Shizi Street No.1 158 box, 215006, Suzhou, Jiangsu, China","institution_ids":["https://openalex.org/I3923682"]},{"raw_affiliation_string":"University of Basque Country, Spanish","institution_ids":["https://openalex.org/I169108374"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4785,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67601891,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"14","issue":"3","first_page":"789","last_page":"804"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9919000267982483,"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":0.9919000267982483,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9916999936103821,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.934499979019165,"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/computer-science","display_name":"Computer science","score":0.790154218673706},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7678000926971436},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6620387434959412},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6012577414512634},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5279514193534851},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.48538482189178467},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4813714623451233},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.480421781539917},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3424259424209595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31602782011032104},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1596394181251526}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.790154218673706},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7678000926971436},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6620387434959412},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6012577414512634},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5279514193534851},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.48538482189178467},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4813714623451233},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.480421781539917},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3424259424209595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31602782011032104},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1596394181251526},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2298/csis170107029z","is_oa":true,"landing_page_url":"https://doi.org/10.2298/csis170107029z","pdf_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02141700029Z","source":{"id":"https://openalex.org/S206939107","display_name":"Computer Science and Information Systems","issn_l":"1820-0214","issn":["1820-0214","2406-1018"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321031","host_organization_name":"ComSIS Consortium","host_organization_lineage":["https://openalex.org/P4310321031"],"host_organization_lineage_names":["ComSIS Consortium"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science and Information Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.2298/csis170107029z","is_oa":true,"landing_page_url":"https://doi.org/10.2298/csis170107029z","pdf_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02141700029Z","source":{"id":"https://openalex.org/S206939107","display_name":"Computer Science and Information Systems","issn_l":"1820-0214","issn":["1820-0214","2406-1018"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321031","host_organization_name":"ComSIS Consortium","host_organization_lineage":["https://openalex.org/P4310321031"],"host_organization_lineage_names":["ComSIS Consortium"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science and Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1055180593","display_name":null,"funder_award_id":"61772355","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G21622510","display_name":null,"funder_award_id":"61303108","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3962253213","display_name":"\u57fa\u4e8e\u652f\u6301\u5411\u91cf\u673a\u7684\u589e\u91cf\u5f0f\u5f3a\u5316\u5b66\u4e60\u6280\u672f\u53ca\u5176\u5e94\u7528\u7814\u7a76","funder_award_id":"61373094","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6223480252","display_name":null,"funder_award_id":"61602332","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7370257148","display_name":null,"funder_award_id":"KJS1524","funder_id":"https://openalex.org/F4320324720","funder_display_name":"Soochow University"},{"id":"https://openalex.org/G7875914319","display_name":null,"funder_award_id":"SYG201422","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8274064415","display_name":null,"funder_award_id":"61702055","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"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320324720","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2755382219.pdf","grobid_xml":"https://content.openalex.org/works/W2755382219.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1508997545","https://openalex.org/W1598083741","https://openalex.org/W1626155273","https://openalex.org/W1986078872","https://openalex.org/W2000875519","https://openalex.org/W2035559399","https://openalex.org/W2113501460","https://openalex.org/W2121863487","https://openalex.org/W2155027007","https://openalex.org/W2165421048","https://openalex.org/W2169209873","https://openalex.org/W2169294731","https://openalex.org/W2240536489","https://openalex.org/W2528069438","https://openalex.org/W2552888796","https://openalex.org/W2965916140","https://openalex.org/W4231095742","https://openalex.org/W4244566287","https://openalex.org/W4298023569"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,5,39],"is":[2,63],"an":[3,18,122],"efficient":[4],"method":[6,49,62,96],"for":[7],"the":[8,14,59,89,92,111,115],"control":[9,45,149],"problem":[10],"by":[11],"interacting":[12],"with":[13,69,109,133,147],"environment":[15],"to":[16,67,120],"get":[17,121],"optimal":[19,123],"policy.":[20],"However,":[21],"it":[22],"al":[23],"so":[24],"faces":[25],"challenges":[26],"such":[27],"as":[28],"low":[29],"convergence":[30,52,56],"accuracy":[31],"and":[32,54,58,97,114],"slow":[33],"convergence.":[34],"More":[35],"over,":[36],"conventional":[37],"reinforcement":[38],"algorithms":[40],"could":[41],"hardly":[42],"solve":[43],"continuous":[44,70,148],"problems.":[46,72],"The":[47,102,137],"kernel-based":[48,99],"can":[50],"accelerate":[51],"speed":[53],"improve":[55],"accuracy;":[57],"policy":[60,124],"gradient":[61],"a":[64,75,106],"good":[65],"way":[66],"deal":[68],"space":[71],"We":[73],"proposed":[74,141],"Sarsa(?)":[76],"version":[77],"of":[78,91],"true":[79],"online":[80],"time":[81],"difference":[82],"algorithm,":[83],"named":[84],"True":[85],"Online":[86],"Sarsa(?)(TOSarsa(?)),":[87],"on":[88],"basis":[90],"clustering-based":[93],"sample":[94],"specification":[95],"selective":[98],"value":[100],"function.":[101],"TOSarsa(?)":[103,132],"algorithm":[104,142],"has":[105],"consistent":[107],"result":[108],"both":[110],"forward":[112],"view":[113,117],"backward":[116],"which":[118],"ensures":[119],"in":[125,145],"less":[126],"time.":[127],"Afterwards":[128],"we":[129],"also":[130],"combined":[131],"heuristic":[134],"dynamic":[135],"programming.":[136],"experiments":[138],"showed":[139],"our":[140],"worked":[143],"well":[144],"dealing":[146],"problem.":[150]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
