{"id":"https://openalex.org/W2980955189","doi":"https://doi.org/10.1109/tcsii.2019.2947682","title":"Reinforcement Learning-Based Control of Nonlinear Systems Using Lyapunov Stability Concept and Fuzzy Reward Scheme","display_name":"Reinforcement Learning-Based Control of Nonlinear Systems Using Lyapunov Stability Concept and Fuzzy Reward Scheme","publication_year":2019,"publication_date":"2019-10-16","ids":{"openalex":"https://openalex.org/W2980955189","doi":"https://doi.org/10.1109/tcsii.2019.2947682","mag":"2980955189"},"language":"en","primary_location":{"id":"doi:10.1109/tcsii.2019.2947682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsii.2019.2947682","pdf_url":null,"source":{"id":"https://openalex.org/S93916849","display_name":"IEEE Transactions on Circuits & Systems II Express Briefs","issn_l":"1549-7747","issn":["1549-7747","1558-3791"],"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 Circuits and Systems II: Express Briefs","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://kclpure.kcl.ac.uk/portal/en/publications/59729b9c-2ccf-479a-a666-bf4a362851f6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100423310","display_name":"Ming Chen","orcid":"https://orcid.org/0000-0003-3404-9278"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Ming Chen","raw_affiliation_strings":["Department of Engineering, King\u2019s College London, London, U.K","Department of Engineering, King's College London, London, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, King\u2019s College London, London, U.K","institution_ids":["https://openalex.org/I183935753"]},{"raw_affiliation_string":"Department of Engineering, King's College London, London, U.K","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059514204","display_name":"Hak\u2010Keung Lam","orcid":"https://orcid.org/0000-0002-6572-7265"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hak Keung Lam","raw_affiliation_strings":["Department of Engineering, King\u2019s College London, London, U.K","Department of Engineering, King's College London, London, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, King\u2019s College London, London, U.K","institution_ids":["https://openalex.org/I183935753"]},{"raw_affiliation_string":"Department of Engineering, King's College London, London, U.K","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070842084","display_name":"Qian Shi","orcid":"https://orcid.org/0000-0003-4623-0576"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qian Shi","raw_affiliation_strings":["Department of Engineering, King\u2019s College London, London, U.K","Department of Engineering, King's College London, London, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, King\u2019s College London, London, U.K","institution_ids":["https://openalex.org/I183935753"]},{"raw_affiliation_string":"Department of Engineering, King's College London, London, U.K","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041909892","display_name":"Bo Xiao","orcid":"https://orcid.org/0000-0001-9361-4340"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bo Xiao","raw_affiliation_strings":["Department of Computing, Imperial College London, London, U.K","Hamlyn Centre for Robotic Surgery, Imperial College London, London, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Computing, Imperial College London, London, U.K","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Hamlyn Centre for Robotic Surgery, Imperial College London, London, U.K","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100423310"],"corresponding_institution_ids":["https://openalex.org/I183935753"],"apc_list":null,"apc_paid":null,"fwci":2.5979,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.9097153,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"67","issue":"10","first_page":"2059","last_page":"2063"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9988999962806702,"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":0.9829999804496765,"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/inverted-pendulum","display_name":"Inverted pendulum","score":0.7828595042228699},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.7181210517883301},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6489157676696777},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5985459089279175},{"id":"https://openalex.org/keywords/fuzzy-control-system","display_name":"Fuzzy control system","score":0.5326606631278992},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5264951586723328},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.5224484801292419},{"id":"https://openalex.org/keywords/lyapunov-stability","display_name":"Lyapunov stability","score":0.5209851861000061},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.518523097038269},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.5007340908050537},{"id":"https://openalex.org/keywords/adaptive-neuro-fuzzy-inference-system","display_name":"Adaptive neuro fuzzy inference system","score":0.4766717255115509},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.472500205039978},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35490936040878296},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3265106976032257},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29144287109375},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17298182845115662}],"concepts":[{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.7828595042228699},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7181210517883301},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6489157676696777},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5985459089279175},{"id":"https://openalex.org/C195975749","wikidata":"https://www.wikidata.org/wiki/Q1475705","display_name":"Fuzzy control system","level":3,"score":0.5326606631278992},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5264951586723328},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.5224484801292419},{"id":"https://openalex.org/C2776829284","wikidata":"https://www.wikidata.org/wiki/Q1341651","display_name":"Lyapunov stability","level":3,"score":0.5209851861000061},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.518523097038269},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.5007340908050537},{"id":"https://openalex.org/C186108316","wikidata":"https://www.wikidata.org/wiki/Q352530","display_name":"Adaptive neuro fuzzy inference system","level":4,"score":0.4766717255115509},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.472500205039978},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35490936040878296},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3265106976032257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29144287109375},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17298182845115662},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tcsii.2019.2947682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsii.2019.2947682","pdf_url":null,"source":{"id":"https://openalex.org/S93916849","display_name":"IEEE Transactions on Circuits & Systems II Express Briefs","issn_l":"1549-7747","issn":["1549-7747","1558-3791"],"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 Circuits and Systems II: Express Briefs","raw_type":"journal-article"},{"id":"pmh:oai:kclpure.kcl.ac.uk:openaire/59729b9c-2ccf-479a-a666-bf4a362851f6","is_oa":true,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/59729b9c-2ccf-479a-a666-bf4a362851f6","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Chen, M, Lam, H K, Shi, Q & Xiao, B 2020, 'Reinforcement Learning-Based Control of Nonlinear Systems Using Lyapunov Stability Concept and Fuzzy Reward Scheme', IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 67, no. 10, 8871158, pp. 2059-2063. https://doi.org/10.1109/TCSII.2019.2947682","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/59729b9c-2ccf-479a-a666-bf4a362851f6","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85092130746&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Chen , M , Lam , H K , Shi , Q & Xiao , B 2020 , ' Reinforcement Learning-Based Control of Nonlinear Systems Using Lyapunov Stability Concept and Fuzzy Reward Scheme ' , IEEE Transactions on Circuits and Systems II: Express Briefs , vol. 67 , no. 10 , 8871158 , pp. 2059-2063 . https://doi.org/10.1109/TCSII.2019.2947682","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:kclpure.kcl.ac.uk:openaire/59729b9c-2ccf-479a-a666-bf4a362851f6","is_oa":true,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/59729b9c-2ccf-479a-a666-bf4a362851f6","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Chen, M, Lam, H K, Shi, Q & Xiao, B 2020, 'Reinforcement Learning-Based Control of Nonlinear Systems Using Lyapunov Stability Concept and Fuzzy Reward Scheme', IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 67, no. 10, 8871158, pp. 2059-2063. https://doi.org/10.1109/TCSII.2019.2947682","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311196","display_name":"King\u2019s College London","ror":"https://ror.org/0220mzb33"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1522301498","https://openalex.org/W1771410628","https://openalex.org/W2035003264","https://openalex.org/W2112964839","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2173248099","https://openalex.org/W2465972538","https://openalex.org/W2605628166","https://openalex.org/W2736601468","https://openalex.org/W2763523689","https://openalex.org/W2768919152","https://openalex.org/W2890218953","https://openalex.org/W2895279298","https://openalex.org/W2898018938","https://openalex.org/W2907594113","https://openalex.org/W2912095073","https://openalex.org/W2915454777","https://openalex.org/W2919115771","https://openalex.org/W2920796978","https://openalex.org/W2921254774","https://openalex.org/W2940927984","https://openalex.org/W2963864421","https://openalex.org/W2971653148","https://openalex.org/W3011120880","https://openalex.org/W4214717370","https://openalex.org/W4289422968","https://openalex.org/W6638018090","https://openalex.org/W6676898700","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W2114654021","https://openalex.org/W2263529430","https://openalex.org/W2389800468","https://openalex.org/W4390103748","https://openalex.org/W2763641192","https://openalex.org/W2150377753","https://openalex.org/W2159724666","https://openalex.org/W2534107666","https://openalex.org/W2117933783","https://openalex.org/W2560479139"],"abstract_inverted_index":{"In":[0,65],"this":[1,51],"brief,":[2],"a":[3,18,55,85],"reinforcement":[4],"learning-based":[5],"control":[6,15,69],"approach":[7,16,70,111],"for":[8],"nonlinear":[9],"systems":[10],"is":[11,90],"presented.":[12],"The":[13,106],"proposed":[14,68,110],"offers":[17],"design":[19,78],"scheme":[20],"of":[21,43,79,96,108],"the":[22,30,40,44,62,67,72,77,80,94,97,109],"adjustable":[23],"policy":[24,46],"learning":[25,41,63],"rate":[26],"(APLR)":[27],"to":[28,59],"reduce":[29],"influence":[31],"imposed":[32],"by":[33,114],"negative":[34],"or":[35],"large":[36],"advantages,":[37],"which":[38],"improves":[39],"stability":[42,74],"proximal":[45],"optimization":[47],"(PPO)":[48],"algorithm.":[49],"Besides,":[50],"brief":[52],"puts":[53],"forward":[54],"Lyapunov-fuzzy":[56],"reward":[57,82,88],"system":[58,83,89,104],"further":[60],"promote":[61],"efficiency.":[64],"addition,":[66],"absorbs":[71],"Lyapunov":[73,81],"concept":[75],"into":[76],"and":[84,101],"particular":[86],"fuzzy":[87,102],"set":[91],"up":[92],"using":[93],"knowledge":[95],"cart-pole":[98],"inverted":[99],"pendulum":[100],"inference":[103],"(FIS).":[105],"merits":[107],"are":[112],"validated":[113],"simulation":[115],"examples.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}