{"id":"https://openalex.org/W4415091331","doi":"https://doi.org/10.1007/s11227-025-07885-5","title":"Homotopic reinforcement learning for distributed consensus control of stochastic Markov jump multi-agent systems","display_name":"Homotopic reinforcement learning for distributed consensus control of stochastic Markov jump multi-agent systems","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4415091331","doi":"https://doi.org/10.1007/s11227-025-07885-5"},"language":"en","primary_location":{"id":"doi:10.1007/s11227-025-07885-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11227-025-07885-5","pdf_url":null,"source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","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":null,"display_name":"Zheng Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126203","display_name":"Hubei University of Automotive Technology","ror":"https://ror.org/039m95m06","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210126203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Yao","raw_affiliation_strings":["School of Robotics and Automation, Hubei University of Automotive Technology, Shiyan, 442002, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Robotics and Automation, Hubei University of Automotive Technology, Shiyan, 442002, China","institution_ids":["https://openalex.org/I4210126203"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qiwu Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Qiwu Zhu","raw_affiliation_strings":["National Rail Transit Electrification and Automation Engineering Technology Research Center (Hong Kong Branch), The Hong Kong Polytechnic University, Hung Hom, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Rail Transit Electrification and Automation Engineering Technology Research Center (Hong Kong Branch), The Hong Kong Polytechnic University, Hung Hom, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109600227","display_name":"Pengjie Qin","orcid":null},"institutions":[{"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":"Pengjie Qin","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 517085, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 517085, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012296164","display_name":"Min Luo","orcid":"https://orcid.org/0009-0002-5432-8821"},"institutions":[{"id":"https://openalex.org/I4210126203","display_name":"Hubei University of Automotive Technology","ror":"https://ror.org/039m95m06","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210126203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Luo","raw_affiliation_strings":["School of Robotics and Automation, Hubei University of Automotive Technology, Shiyan, 442002, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Robotics and Automation, Hubei University of Automotive Technology, Shiyan, 442002, China","institution_ids":["https://openalex.org/I4210126203"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":{"value":3290,"currency":"USD","value_usd":3290},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23680372,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"81","issue":"15","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9957000017166138,"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":0.9922000169754028,"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":0.6280999779701233},{"id":"https://openalex.org/keywords/consensus","display_name":"Consensus","score":0.6033999919891357},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5634999871253967},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5512999892234802},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4652999937534332},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.46219998598098755},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.446399986743927},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.39399999380111694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8309000134468079},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6280999779701233},{"id":"https://openalex.org/C107107730","wikidata":"https://www.wikidata.org/wiki/Q2994424","display_name":"Consensus","level":3,"score":0.6033999919891357},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5634999871253967},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5512999892234802},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.49709999561309814},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4652999937534332},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.46219998598098755},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.446399986743927},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.39399999380111694},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C2780695682","wikidata":"https://www.wikidata.org/wiki/Q4005959","display_name":"Jump","level":2,"score":0.3675000071525574},{"id":"https://openalex.org/C2776829284","wikidata":"https://www.wikidata.org/wiki/Q1341651","display_name":"Lyapunov stability","level":3,"score":0.365200012922287},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.3589000105857849},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.32170000672340393},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C2983222225","wikidata":"https://www.wikidata.org/wiki/Q2994424","display_name":"Consensus algorithm","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.271699994802475},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.2644999921321869}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11227-025-07885-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11227-025-07885-5","pdf_url":null,"source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/118214","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/118214","pdf_url":null,"source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal/Magazine Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1630241696","https://openalex.org/W1966751197","https://openalex.org/W2024303516","https://openalex.org/W2088103590","https://openalex.org/W2107674817","https://openalex.org/W2107726111","https://openalex.org/W2136677890","https://openalex.org/W2148439597","https://openalex.org/W2153573511","https://openalex.org/W2249859651","https://openalex.org/W2346408824","https://openalex.org/W2467518411","https://openalex.org/W2740962288","https://openalex.org/W2772589676","https://openalex.org/W2789870819","https://openalex.org/W2790351206","https://openalex.org/W2794027470","https://openalex.org/W3025384446","https://openalex.org/W3043736797","https://openalex.org/W3047879910","https://openalex.org/W3183428472","https://openalex.org/W4210732025","https://openalex.org/W4214523407","https://openalex.org/W4221102161","https://openalex.org/W4285505520","https://openalex.org/W4293188401","https://openalex.org/W4307776787","https://openalex.org/W4389331418","https://openalex.org/W4390534339","https://openalex.org/W4393200190","https://openalex.org/W4394737824","https://openalex.org/W4399568695","https://openalex.org/W4401536639","https://openalex.org/W4409126375"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-13T00:00:00"}
