{"id":"https://openalex.org/W4386363016","doi":"https://doi.org/10.1109/tsmc.2023.3305498","title":"Efficient Incremental Offline Reinforcement Learning With Sparse Broad Critic Approximation","display_name":"Efficient Incremental Offline Reinforcement Learning With Sparse Broad Critic Approximation","publication_year":2023,"publication_date":"2023-09-01","ids":{"openalex":"https://openalex.org/W4386363016","doi":"https://doi.org/10.1109/tsmc.2023.3305498"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2023.3305498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2023.3305498","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"},"type":"article","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/A5084833652","display_name":"Liang Yao","orcid":"https://orcid.org/0000-0003-3377-1509"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":true,"raw_author_name":"Liang Yao","raw_affiliation_strings":["Department of Electromechanical Engineering, University of Macau, Macau, China"],"affiliations":[{"raw_affiliation_string":"Department of Electromechanical Engineering, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042608392","display_name":"Baoliang Zhao","orcid":"https://orcid.org/0000-0002-8157-5951"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoliang Zhao","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"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 Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100689411","display_name":"Ziwen Wang","orcid":"https://orcid.org/0000-0003-0688-3564"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziwen Wang","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063490642","display_name":"Pak Kin Wong","orcid":"https://orcid.org/0000-0002-7623-6904"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Pak Kin Wong","raw_affiliation_strings":["Department of Electromechanical Engineering, University of Macau, Macau, China"],"affiliations":[{"raw_affiliation_string":"Department of Electromechanical Engineering, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668236","display_name":"Ying Hu","orcid":"https://orcid.org/0000-0002-3807-3649"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Hu","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5084833652"],"corresponding_institution_ids":["https://openalex.org/I204512498"],"apc_list":null,"apc_paid":null,"fwci":2.7733,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.92033452,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"54","issue":"1","first_page":"156","last_page":"169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9983999729156494,"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":0.9983999729156494,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.9955999851226807,"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/T12676","display_name":"Machine Learning and ELM","score":0.9866999983787537,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7436782121658325},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.679226279258728},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.6777956485748291},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6209269165992737},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5970463752746582},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5048011541366577},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.5003397464752197},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.4773987829685211},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4407661557197571},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4286136031150818},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.4189170002937317},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4149576425552368},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35424304008483887},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15211722254753113},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.151706725358963},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.10688915848731995}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7436782121658325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.679226279258728},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.6777956485748291},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6209269165992737},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5970463752746582},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5048011541366577},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5003397464752197},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4773987829685211},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4407661557197571},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4286136031150818},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.4189170002937317},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4149576425552368},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35424304008483887},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15211722254753113},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.151706725358963},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.10688915848731995},{"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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":1,"locations":[{"id":"doi:10.1109/tsmc.2023.3305498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2023.3305498","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G1500225812","display_name":null,"funder_award_id":"62273328","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2479525681","display_name":null,"funder_award_id":"2022-KF-22-07","funder_id":"https://openalex.org/F4320326907","funder_display_name":"State Key Laboratory of Robotics"},{"id":"https://openalex.org/G3098320488","display_name":null,"funder_award_id":"JCYJ20200109115201707","funder_id":"https://openalex.org/F4320329791","funder_display_name":"Shenzhen Fundamental Research Program"},{"id":"https://openalex.org/G3387435421","display_name":null,"funder_award_id":"2022YFB4703500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5267426585","display_name":null,"funder_award_id":"U21A20489","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/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320326907","display_name":"State Key Laboratory of Robotics","ror":null},{"id":"https://openalex.org/F4320329791","display_name":"Shenzhen Fundamental Research Program","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1977655452","https://openalex.org/W1978023077","https://openalex.org/W2082511574","https://openalex.org/W2113921460","https://openalex.org/W2118556122","https://openalex.org/W2130599357","https://openalex.org/W2135046866","https://openalex.org/W2169440744","https://openalex.org/W2344415132","https://openalex.org/W2586680856","https://openalex.org/W2738226240","https://openalex.org/W2742454413","https://openalex.org/W2772589676","https://openalex.org/W2789837488","https://openalex.org/W2796202072","https://openalex.org/W2890126432","https://openalex.org/W2947832046","https://openalex.org/W2955130115","https://openalex.org/W2959895084","https://openalex.org/W2967043083","https://openalex.org/W2972985782","https://openalex.org/W2993548219","https://openalex.org/W3004840042","https://openalex.org/W3011978531","https://openalex.org/W3046560447","https://openalex.org/W3090832565","https://openalex.org/W3115913152","https://openalex.org/W3157010837","https://openalex.org/W3202358609","https://openalex.org/W4200114506","https://openalex.org/W4226518300","https://openalex.org/W4292363360","https://openalex.org/W4295832261","https://openalex.org/W6676931166","https://openalex.org/W6679630895","https://openalex.org/W6684488654"],"related_works":["https://openalex.org/W2140186469","https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W4389724018","https://openalex.org/W4318719684","https://openalex.org/W3183136280","https://openalex.org/W4318559728","https://openalex.org/W2775233965","https://openalex.org/W4294241976","https://openalex.org/W3215067404"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2,76,87],"(ORL)":[3],"has":[4,79],"been":[5,80,95],"getting":[6],"increasing":[7],"attention":[8],"in":[9,40,54,83,88,125,152,209,218],"robot":[10],"learning,":[11],"benefiting":[12],"from":[13,24],"its":[14,44,139],"ability":[15,161],"to":[16,43,67],"avoid":[17],"hazardous":[18],"exploration":[19],"and":[20,57,70,85,133,136,157,162,179,225],"learn":[21],"policies":[22],"directly":[23],"precollected":[25],"samples.":[26],"Approximate":[27],"policy":[28],"iteration":[29],"(API)":[30],"is":[31,65,113,144,223,233],"one":[32],"of":[33,47,63,118,148,155,165,207,244],"the":[34,116,122,145,153,180,184,205,242],"most":[35],"commonly":[36],"investigated":[37],"ORL":[38,105],"approaches":[39],"robotics,":[41],"due":[42],"linear":[45,127],"representation":[46],"policies,":[48],"which":[49,120],"makes":[50],"it":[51],"fairly":[52],"transparent":[53],"both":[55],"theoretical":[56],"engineering":[58],"analysis.":[59],"One":[60],"open":[61],"problem":[62,217],"API":[64,149,195],"how":[66],"design":[68],"efficient":[69],"effective":[71],"basis":[72],"functions.":[73],"The":[74,142,159,238],"broad":[75,109,140],"system":[77],"(BLS)":[78],"extensively":[81],"studied":[82],"supervised":[84],"unsupervised":[86],"various":[89],"applications.":[90],"However,":[91],"few":[92],"investigations":[93],"have":[94],"conducted":[96,175],"on":[97,176,236],"ORL.":[98,158],"In":[99],"this":[100],"article,":[101],"a":[102,126,213,226],"novel":[103],"incremental":[104],"approach":[106],"with":[107,115,129,150,247],"sparse":[108,132],"critic":[110,123],"approximation":[111,160],"(BORL)":[112],"proposed":[114,185,234],"advantages":[117,243],"BLS,":[119],"approximates":[121],"function":[124],"manner":[128],"randomly":[130],"projected":[131],"compact":[134],"features":[135],"dynamically":[137],"expands":[138],"structure.":[141],"BORL":[143,166,186,208],"first":[146],"extension":[147],"BLS":[151],"field":[154],"robotics":[156],"convergence":[163],"performance":[164,192],"are":[167,173],"also":[168],"analyzed.":[169],"Comprehensive":[170],"simulation":[171],"studies":[172],"then":[174],"two":[177],"benchmarks,":[178],"results":[181,240],"demonstrate":[182,204,241],"that":[183],"can":[187],"obtain":[188],"comparable":[189],"or":[190],"better":[191],"than":[193],"conventional":[194,248],"methods":[196],"without":[197],"laborious":[198],"hyperparameter":[199],"fine-tuning":[200],"work.":[201],"To":[202],"further":[203],"effectiveness":[206],"practical":[210],"robotic":[211,219],"applications,":[212],"variable":[214],"force":[215,249],"tracking":[216,250],"ultrasound":[220],"scanning":[221],"(RUSS)":[222],"investigated,":[224],"learning-based":[227],"adaptive":[228],"impedance":[229],"control":[230],"(LAIC)":[231],"algorithm":[232],"based":[235],"BORL.":[237],"experimental":[239],"LAIC":[245],"compared":[246],"methods.":[251]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}