{"id":"https://openalex.org/W2580133360","doi":"https://doi.org/10.1109/tnnls.2017.2650943","title":"Manifold Regularized Reinforcement Learning","display_name":"Manifold Regularized Reinforcement Learning","publication_year":2017,"publication_date":"2017-01-27","ids":{"openalex":"https://openalex.org/W2580133360","doi":"https://doi.org/10.1109/tnnls.2017.2650943","mag":"2580133360","pmid":"https://pubmed.ncbi.nlm.nih.gov/28141532"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2017.2650943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2017.2650943","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/A5100442403","display_name":"Hongliang Li","orcid":"https://orcid.org/0000-0001-5387-0825"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongliang Li","raw_affiliation_strings":["Tencent Inc., Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5387-0825","affiliations":[{"raw_affiliation_string":"Tencent Inc., Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004057129","display_name":"Derong Liu","orcid":"https://orcid.org/0000-0003-3715-4778"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Derong Liu","raw_affiliation_strings":["School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3715-4778","affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024549341","display_name":"Ding Wang","orcid":"https://orcid.org/0000-0002-7149-5712"},"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ding Wang","raw_affiliation_strings":["State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7149-5712","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":1.8251,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.88331807,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"29","issue":"4","first_page":"932","last_page":"943"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9991000294685364,"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.9648000001907349,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8616987466812134},{"id":"https://openalex.org/keywords/manifold","display_name":"Manifold (fluid mechanics)","score":0.5844768285751343},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5794452428817749},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.570088267326355},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.5667450428009033},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5542317628860474},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5277486443519592},{"id":"https://openalex.org/keywords/nonlinear-dimensionality-reduction","display_name":"Nonlinear dimensionality reduction","score":0.47182804346084595},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.45414966344833374},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4468532204627991},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43629997968673706},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4273719787597656},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4176701605319977},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4110746383666992},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.39566150307655334},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3934164345264435},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28466886281967163},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.2808803915977478},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0852992832660675}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8616987466812134},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.5844768285751343},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5794452428817749},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.570088267326355},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.5667450428009033},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5542317628860474},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5277486443519592},{"id":"https://openalex.org/C151876577","wikidata":"https://www.wikidata.org/wiki/Q7049464","display_name":"Nonlinear dimensionality reduction","level":3,"score":0.47182804346084595},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.45414966344833374},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4468532204627991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43629997968673706},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4273719787597656},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4176701605319977},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4110746383666992},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.39566150307655334},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3934164345264435},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28466886281967163},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.2808803915977478},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0852992832660675},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2017.2650943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2017.2650943","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:28141532","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28141532","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":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G1278371216","display_name":null,"funder_award_id":"4162065","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G2801732935","display_name":null,"funder_award_id":"61 273140","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G560465369","display_name":null,"funder_award_id":"U1501251","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5871946117","display_name":null,"funder_award_id":"61503377","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6391760457","display_name":null,"funder_award_id":"61304086","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7163010157","display_name":"\u57fa\u4e8e\u6570\u636e\u7684\u5efa\u7b51\u7fa4\u53ca\u5206\u5e03\u5f0f\u80fd\u6e90\u7cfb\u7edf\u4e00\u4f53\u5316\u5efa\u6a21\u4e0e\u81ea\u5b66\u4e60\u4f18\u5316\u63a7\u5236","funder_award_id":"61533017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8230378891","display_name":"\u590d\u6742\u7cfb\u7edf\u5e73\u884c\u63a7\u5236\u57fa\u7840\u7406\u8bba\u53ca\u5178\u578b\u5e94\u7528","funder_award_id":"61233001","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/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W192920577","https://openalex.org/W560518094","https://openalex.org/W1507222174","https://openalex.org/W1544439040","https://openalex.org/W1601081659","https://openalex.org/W1617381654","https://openalex.org/W1664825283","https://openalex.org/W1730555343","https://openalex.org/W1986864433","https://openalex.org/W1988523476","https://openalex.org/W1989368986","https://openalex.org/W1989855774","https://openalex.org/W1997112725","https://openalex.org/W1999678919","https://openalex.org/W2001141328","https://openalex.org/W2011310556","https://openalex.org/W2014729048","https://openalex.org/W2028599032","https://openalex.org/W2030038728","https://openalex.org/W2032378315","https://openalex.org/W2042184006","https://openalex.org/W2047081066","https://openalex.org/W2050838777","https://openalex.org/W2052399669","https://openalex.org/W2053186076","https://openalex.org/W2054083798","https://openalex.org/W2068764432","https://openalex.org/W2068949505","https://openalex.org/W2072054128","https://openalex.org/W2072931156","https://openalex.org/W2073384958","https://openalex.org/W2081758070","https://openalex.org/W2086608109","https://openalex.org/W2093524643","https://openalex.org/W2097308346","https://openalex.org/W2104290444","https://openalex.org/W2104753538","https://openalex.org/W2112264645","https://openalex.org/W2118556122","https://openalex.org/W2121863487","https://openalex.org/W2124144580","https://openalex.org/W2125191551","https://openalex.org/W2125710293","https://openalex.org/W2128152413","https://openalex.org/W2130599357","https://openalex.org/W2132301339","https://openalex.org/W2132351269","https://openalex.org/W2134284153","https://openalex.org/W2135574445","https://openalex.org/W2145060720","https://openalex.org/W2145339207","https://openalex.org/W2154997814","https://openalex.org/W2158738729","https://openalex.org/W2161795906","https://openalex.org/W2177967097","https://openalex.org/W2257979135","https://openalex.org/W2290874868","https://openalex.org/W2312998612","https://openalex.org/W2487144912","https://openalex.org/W2586680856","https://openalex.org/W2997701990","https://openalex.org/W3018189936","https://openalex.org/W3027095131","https://openalex.org/W4205326910","https://openalex.org/W4214717370","https://openalex.org/W4285719527","https://openalex.org/W4299401133","https://openalex.org/W6632910978","https://openalex.org/W6637179743","https://openalex.org/W6637597983","https://openalex.org/W6675747103","https://openalex.org/W6678573530","https://openalex.org/W6678588739","https://openalex.org/W6679599164","https://openalex.org/W6679630895","https://openalex.org/W6680088802","https://openalex.org/W6681439324","https://openalex.org/W6683356630","https://openalex.org/W6683841269","https://openalex.org/W6696866154"],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2903299703","https://openalex.org/W2156021013","https://openalex.org/W2016648086","https://openalex.org/W3105579180","https://openalex.org/W4281791088","https://openalex.org/W4297823484"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,52],"novel":[4,58],"manifold":[5,29],"regularized":[6],"reinforcement":[7],"learning":[8,62],"scheme":[9,50,70,95],"for":[10,18,57],"continuous":[11],"Markov":[12],"decision":[13],"processes.":[14],"Smooth":[15],"feature":[16],"representations":[17],"value":[19],"function":[20],"approximation":[21],"can":[22,38,100],"be":[23,39],"automatically":[24],"learned":[25,33],"using":[26],"the":[27,42,45,49,68,79,83,90,93],"unsupervised":[28],"regularization":[30],"method.":[31],"The":[32,65],"features":[34],"are":[35],"data-driven,":[36],"and":[37,63,82,96],"adapted":[40],"to":[41],"geometry":[43],"of":[44,67,92],"state":[46],"space.":[47],"Furthermore,":[48],"provides":[51],"direct":[53],"basis":[54],"representation":[55],"extension":[56],"samples":[59],"during":[60],"policy":[61],"control.":[64],"performance":[66],"proposed":[69,94],"is":[71],"evaluated":[72],"on":[73],"two":[74],"benchmark":[75],"control":[76],"tasks,":[77],"i.e.,":[78],"inverted":[80],"pendulum":[81],"energy":[84],"storage":[85],"problem.":[86],"Simulation":[87],"results":[88],"illustrate":[89],"concepts":[91],"show":[97],"that":[98],"it":[99],"obtain":[101],"excellent":[102],"performance.":[103]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}