{"id":"https://openalex.org/W7148504081","doi":"https://doi.org/10.1109/lcsys.2026.3680273","title":"Policy Iteration with Non-Asymptotic Convergence for Systems with Random Parameters","display_name":"Policy Iteration with Non-Asymptotic Convergence for Systems with Random Parameters","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7148504081","doi":"https://doi.org/10.1109/lcsys.2026.3680273"},"language":null,"primary_location":{"id":"doi:10.1109/lcsys.2026.3680273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2026.3680273","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"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 Control Systems Letters","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/A5032771161","display_name":"Jing Lai","orcid":"https://orcid.org/0000-0002-9920-0066"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Lai","raw_affiliation_strings":["Department of Automation, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-9920-0066","affiliations":[{"raw_affiliation_string":"Department of Automation, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103585690","display_name":"Wenwu Fan","orcid":"https://orcid.org/0000-0002-7310-0382"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwu Fan","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-7310-0382","affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132770324","display_name":"Junlin Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlin Xiong","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-0128-4960","affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122029975","display_name":"Kaiyun Xie","orcid":"https://orcid.org/0000-0002-4709-5508"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiyun Xie","raw_affiliation_strings":["Department of Automation, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-4709-5508","affiliations":[{"raw_affiliation_string":"Department of Automation, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yu Kang","orcid":"https://orcid.org/0000-0002-8706-3252"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Kang","raw_affiliation_strings":["Department of Automation, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-8706-3252","affiliations":[{"raw_affiliation_string":"Department of Automation, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48194552,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.1988999992609024,"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":0.1988999992609024,"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/T11413","display_name":"Risk and Portfolio Optimization","score":0.121799997985363,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10545","display_name":"Optimization and Variational Analysis","score":0.06289999932050705,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5884000062942505},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.319599986076355},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.31619998812675476},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.3005000054836273},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2833000123500824},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.27309998869895935}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5884000062942505},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.47540000081062317},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4553000032901764},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4255000054836273},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41339999437332153},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2818000018596649},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C2986577269","wikidata":"https://www.wikidata.org/wiki/Q11306265","display_name":"Random noise","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lcsys.2026.3680273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2026.3680273","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"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 Control Systems Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.42720648646354675,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,28,51,62,79,84],"infinite-horizon":[4],"linear":[5],"quadratic":[6],"regulator":[7],"problem":[8],"for":[9,27,72],"discrete-time":[10],"systems":[11],"with":[12,90],"random":[13],"parameters.":[14],"A":[15,39],"novel":[16,63],"matrix":[17,64],"norm":[18],"is":[19,46,70,88,96],"introduced":[20],"to":[21,49],"establish":[22],"a":[23,66],"non-asymptotic":[24,67],"convergence":[25,68],"analysis":[26,69],"model-based":[29],"policy":[30,42,54,87],"iteration,":[31],"providing":[32],"an":[33],"explicit":[34],"and":[35,82],"quantifiable":[36],"contraction":[37],"rate.":[38],"normalized":[40],"model-free":[41],"iteration":[43],"(NMFPI)":[44],"algorithm":[45,95],"then":[47],"proposed":[48,94],"learn":[50],"optimal":[52],"control":[53,86],"directly":[55],"using":[56],"offline":[57],"system":[58],"trajectories.":[59],"Based":[60],"on":[61],"norm,":[65],"conducted":[71],"NMFPI,":[73],"which":[74],"shows":[75],"error":[76],"propagation":[77],"through":[78,98],"learning":[80],"process":[81],"ensures":[83],"learned":[85],"near-optimal":[89],"high":[91],"probability.":[92],"The":[93],"illustrated":[97],"several":[99],"examples.":[100]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-03T00:00:00"}