{"id":"https://openalex.org/W4396653811","doi":"https://doi.org/10.1080/23307706.2024.2345664","title":"A homotopy-based reinforcement learning scheme to optimal control for Markov switched interconnected systems","display_name":"A homotopy-based reinforcement learning scheme to optimal control for Markov switched interconnected systems","publication_year":2024,"publication_date":"2024-05-05","ids":{"openalex":"https://openalex.org/W4396653811","doi":"https://doi.org/10.1080/23307706.2024.2345664"},"language":"en","primary_location":{"id":"doi:10.1080/23307706.2024.2345664","is_oa":false,"landing_page_url":"https://doi.org/10.1080/23307706.2024.2345664","pdf_url":null,"source":{"id":"https://openalex.org/S2475925340","display_name":"Journal of Control and Decision","issn_l":"2330-7706","issn":["2330-7706","2330-7714"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Control and Decision","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/A5030346561","display_name":"Jinxu Liu","orcid":"https://orcid.org/0000-0002-4661-6877"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinxu Liu","raw_affiliation_strings":["Anhui University of Technology","School of Electrical and Information Engineering, Anhui University of Technology, Ma'anshan, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui University of Technology","institution_ids":["https://openalex.org/I92178344"]},{"raw_affiliation_string":"School of Electrical and Information Engineering, Anhui University of Technology, Ma'anshan, People's Republic of China","institution_ids":["https://openalex.org/I92178344"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025730961","display_name":"Xuanrui Mi","orcid":"https://orcid.org/0009-0009-9059-2161"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanrui Mi","raw_affiliation_strings":["Anhui University of Technology","School of Electrical and Information Engineering, Anhui University of Technology, Ma'anshan, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui University of Technology","institution_ids":["https://openalex.org/I92178344"]},{"raw_affiliation_string":"School of Electrical and Information Engineering, Anhui University of Technology, Ma'anshan, People's Republic of China","institution_ids":["https://openalex.org/I92178344"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007027701","display_name":"Jianwei Xia","orcid":"https://orcid.org/0000-0002-5330-9349"},"institutions":[{"id":"https://openalex.org/I196934937","display_name":"Liaocheng University","ror":"https://ror.org/03yh0n709","country_code":"CN","type":"education","lineage":["https://openalex.org/I196934937"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwei Xia","raw_affiliation_strings":["Liaocheng University","School of Mathematical Sciences, Liaocheng University, Liaocheng, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Liaocheng University","institution_ids":["https://openalex.org/I196934937"]},{"raw_affiliation_string":"School of Mathematical Sciences, Liaocheng University, Liaocheng, People's Republic of China","institution_ids":["https://openalex.org/I196934937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072342922","display_name":"Lei Su","orcid":"https://orcid.org/0000-0001-8728-0583"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lei Su","raw_affiliation_strings":["Anhui University of Technology","School of Electrical and Information Engineering, Anhui University of Technology, Ma'anshan, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui University of Technology","institution_ids":["https://openalex.org/I92178344"]},{"raw_affiliation_string":"School of Electrical and Information Engineering, Anhui University of Technology, Ma'anshan, People's Republic of China","institution_ids":["https://openalex.org/I92178344"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067323219","display_name":"Hao Shen","orcid":"https://orcid.org/0000-0001-7024-6573"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Shen","raw_affiliation_strings":["Anhui University of Technology","School of Electrical and Information Engineering, Anhui University of Technology, Ma'anshan, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui University of Technology","institution_ids":["https://openalex.org/I92178344"]},{"raw_affiliation_string":"School of Electrical and Information Engineering, Anhui University of Technology, Ma'anshan, People's Republic of China","institution_ids":["https://openalex.org/I92178344"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5072342922"],"corresponding_institution_ids":["https://openalex.org/I92178344"],"apc_list":null,"apc_paid":null,"fwci":1.3019,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80909691,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"13","issue":"2","first_page":"383","last_page":"398"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9952999949455261,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8271839618682861},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.7011480331420898},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5833871364593506},{"id":"https://openalex.org/keywords/homotopy","display_name":"Homotopy","score":0.5163828134536743},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.490626722574234},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.48920392990112305},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.48291346430778503},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47507303953170776},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.45245417952537537},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4282102882862091},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4213227927684784},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4062989354133606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25326353311538696},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1815280020236969}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8271839618682861},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.7011480331420898},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5833871364593506},{"id":"https://openalex.org/C5961521","wikidata":"https://www.wikidata.org/wiki/Q746083","display_name":"Homotopy","level":2,"score":0.5163828134536743},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.490626722574234},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.48920392990112305},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.48291346430778503},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47507303953170776},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.45245417952537537},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4282102882862091},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4213227927684784},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4062989354133606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25326353311538696},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1815280020236969},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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":1,"locations":[{"id":"doi:10.1080/23307706.2024.2345664","is_oa":false,"landing_page_url":"https://doi.org/10.1080/23307706.2024.2345664","pdf_url":null,"source":{"id":"https://openalex.org/S2475925340","display_name":"Journal of Control and Decision","issn_l":"2330-7706","issn":["2330-7706","2330-7714"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Control and Decision","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G27161139","display_name":null,"funder_award_id":"62103005, 62173001 and 62273006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8622580240","display_name":null,"funder_award_id":"2022AH020034","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1763243278","https://openalex.org/W1964752273","https://openalex.org/W2011537986","https://openalex.org/W2020580820","https://openalex.org/W2031780472","https://openalex.org/W2036378401","https://openalex.org/W2037025184","https://openalex.org/W2037191857","https://openalex.org/W2111836897","https://openalex.org/W2152170081","https://openalex.org/W2155693480","https://openalex.org/W2163516029","https://openalex.org/W2166103243","https://openalex.org/W2279381790","https://openalex.org/W2640191396","https://openalex.org/W2796158757","https://openalex.org/W2982838649","https://openalex.org/W3047221759","https://openalex.org/W3129701104","https://openalex.org/W3214995827","https://openalex.org/W3216539601","https://openalex.org/W4205713825","https://openalex.org/W4210732025","https://openalex.org/W4229881203","https://openalex.org/W4230728348","https://openalex.org/W4242025301","https://openalex.org/W4243051935","https://openalex.org/W4245305869","https://openalex.org/W4245573583","https://openalex.org/W4248177570","https://openalex.org/W4285505520","https://openalex.org/W4294204251","https://openalex.org/W4294326629","https://openalex.org/W4297001401","https://openalex.org/W4298008826","https://openalex.org/W4306946228","https://openalex.org/W4310329823","https://openalex.org/W4318606467","https://openalex.org/W4322102674","https://openalex.org/W4364856517","https://openalex.org/W4384927649","https://openalex.org/W4387886154","https://openalex.org/W4390776948","https://openalex.org/W6637992504","https://openalex.org/W6729518879"],"related_works":["https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W2808418668","https://openalex.org/W3096874164","https://openalex.org/W2357975469","https://openalex.org/W2937181779","https://openalex.org/W2145363145"],"abstract_inverted_index":{"In":[0,69],"this":[1,70],"paper,":[2],"a":[3,54,66,72,99,103],"homotopy-based":[4,55],"reinforcement":[5,74],"learning":[6,29,75],"optimal":[7,82],"control":[8,30],"method":[9,26,76,95],"is":[10,44,58,77,96],"developed":[11],"for":[12,84],"Markov":[13,85],"switched":[14,86],"interconnected":[15,87],"systems":[16],"with":[17,41,48],"unknown":[18],"system":[19],"dynamics.":[20],"By":[21],"utilising":[22],"the":[23,32,35,49,81,90,93],"subsystem":[24],"decomposition":[25],"and":[27,102],"parallel":[28],"method,":[31],"solution":[33],"of":[34,51,92],"game":[36],"coupled":[37],"algebraic":[38],"Riccati":[39],"equations":[40],"jumping":[42],"parameters":[43],"approximated.":[45],"To":[46],"dispense":[47],"requirement":[50],"initial":[52],"stability,":[53],"policy":[56],"iteration":[57],"introduced,":[59],"which":[60],"can":[61],"place":[62],"unstable":[63],"poles":[64],"into":[65],"stable":[67],"plane.":[68],"regard,":[71],"model-free":[73],"presented":[78],"to":[79],"design":[80],"controller":[83],"systems.":[88],"Finally,":[89],"effectiveness":[91],"proposed":[94],"verified":[97],"by":[98],"numerical":[100],"example":[101],"practical":[104],"example.":[105]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}