{"id":"https://openalex.org/W2029498761","doi":"https://doi.org/10.1109/adprl.2011.5967377","title":"Adaptive sample collection using active learning for kernel-based approximate policy iteration","display_name":"Adaptive sample collection using active learning for kernel-based approximate policy iteration","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2029498761","doi":"https://doi.org/10.1109/adprl.2011.5967377","mag":"2029498761"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2011.5967377","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5100623405","display_name":"Chunming Liu","orcid":"https://orcid.org/0000-0002-0564-4476"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunming Liu","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053112608","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-3238-745X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102572048","display_name":"Haiyun Hu","orcid":"https://orcid.org/0000-0002-2358-9116"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyun Hu","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005995567","display_name":"Bin Dai","orcid":"https://orcid.org/0000-0001-9405-2626"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Dai","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"56","last_page":"61"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973999857902527,"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":0.9973999857902527,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.9965000152587891,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9943000078201294,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7485761642456055},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7103250026702881},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6990762948989868},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.563930094242096},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.5014007091522217},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4999051094055176},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.46573320031166077},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.45600804686546326},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.4319094121456146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42686164379119873},{"id":"https://openalex.org/keywords/radial-basis-function-kernel","display_name":"Radial basis function kernel","score":0.41387107968330383},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3619343340396881},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3283151090145111},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2377634048461914},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.21297824382781982},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.07667627930641174}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7485761642456055},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7103250026702881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6990762948989868},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.563930094242096},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.5014007091522217},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4999051094055176},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.46573320031166077},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.45600804686546326},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.4319094121456146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42686164379119873},{"id":"https://openalex.org/C75866337","wikidata":"https://www.wikidata.org/wiki/Q7280263","display_name":"Radial basis function kernel","level":4,"score":0.41387107968330383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3619343340396881},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3283151090145111},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2377634048461914},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.21297824382781982},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.07667627930641174},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/adprl.2011.5967377","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2082691056","https://openalex.org/W2084202551","https://openalex.org/W2096258902","https://openalex.org/W2107726111","https://openalex.org/W2118556122","https://openalex.org/W2148603752","https://openalex.org/W2150923691","https://openalex.org/W2153290280","https://openalex.org/W2160095661","https://openalex.org/W2161966552","https://openalex.org/W2319588593","https://openalex.org/W2489939061","https://openalex.org/W2586680856","https://openalex.org/W2911283634","https://openalex.org/W4285719527","https://openalex.org/W6671393130","https://openalex.org/W6682443896","https://openalex.org/W6683603353","https://openalex.org/W6689723076","https://openalex.org/W7071374342"],"related_works":["https://openalex.org/W127070535","https://openalex.org/W2140869420","https://openalex.org/W2357150443","https://openalex.org/W1519806901","https://openalex.org/W1603091392","https://openalex.org/W2348982811","https://openalex.org/W2958374823","https://openalex.org/W3021988786","https://openalex.org/W1584947872","https://openalex.org/W2354280465"],"abstract_inverted_index":{"Approximate":[0],"policy":[1,67],"iteration":[2,68],"(API)":[3],"has":[4],"been":[5],"shown":[6],"to":[7,31,52,73],"be":[8,87,112],"a":[9,40],"class":[10],"of":[11,34,56,109],"reinforcement":[12],"learning":[13,97],"methods":[14],"with":[15],"stability":[16],"and":[17,77],"sample":[18,21,43],"efficiency.":[19],"However,":[20],"collection":[22,44],"is":[23,29,50,71],"still":[24],"an":[25,62],"open":[26],"problem":[27],"which":[28],"critical":[30],"the":[32,54,79,104,107],"performance":[33,55,108],"API":[35],"methods.":[36],"In":[37,59],"this":[38,60],"paper,":[39],"novel":[41],"adaptive":[42],"strategy":[45],"using":[46,103],"active":[47],"learning-based":[48],"exploration":[49],"proposed":[51,105],"enhance":[53],"kernel-based":[57,64],"API.":[58],"strategy,":[61,106],"online":[63],"least":[65],"squares":[66],"(KLSPI)":[69],"method":[70],"adopted":[72],"construct":[74],"nonlinear":[75],"features":[76],"approximate":[78],"Q-function":[80],"simultaneously.":[81],"Therefore,":[82],"more":[83],"representative":[84],"samples":[85],"can":[86,111],"obtained":[88],"for":[89],"value":[90],"function":[91],"approximation.":[92],"Simulation":[93],"results":[94],"on":[95],"typical":[96],"control":[98],"problems":[99],"illustrate":[100],"that":[101],"by":[102],"KLSPI":[110],"improved":[113],"remarkably.":[114]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}