{"id":"https://openalex.org/W4411551092","doi":"https://doi.org/10.1109/tac.2025.3582529","title":"Off-Policy Reinforcement Learning for $H_\\infty$ Control of Linear Discrete-Time Systems With Network-Induced Dropouts","display_name":"Off-Policy Reinforcement Learning for $H_\\infty$ Control of Linear Discrete-Time Systems With Network-Induced Dropouts","publication_year":2025,"publication_date":"2025-06-23","ids":{"openalex":"https://openalex.org/W4411551092","doi":"https://doi.org/10.1109/tac.2025.3582529"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2025.3582529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3582529","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","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/A5100396295","display_name":"Yi Jiang","orcid":"https://orcid.org/0000-0001-8927-0119"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Jiang","raw_affiliation_strings":["School of Artificial Intelligence and Automation, the Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China, and the Hubei Key Laboratory of Brain-Inspired Intelligent Systems, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, the Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China, and the Hubei Key Laboratory of Brain-Inspired Intelligent Systems, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014234601","display_name":"Tao Yang","orcid":"https://orcid.org/0000-0003-4090-8497"},"institutions":[{"id":"https://openalex.org/I4391767858","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Yang","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756","https://openalex.org/I4391767858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040120960","display_name":"Weinan Gao","orcid":"https://orcid.org/0000-0001-7921-018X"},"institutions":[{"id":"https://openalex.org/I4391767858","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weinan Gao","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756","https://openalex.org/I4391767858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078883186","display_name":"Jin Wu","orcid":"https://orcid.org/0000-0001-5930-4170"},"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":"Jin Wu","raw_affiliation_strings":["School of Intelligent Science and Technology, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Intelligent Science and Technology, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042520521","display_name":"Tianyou Chai","orcid":"https://orcid.org/0000-0002-4623-1483"},"institutions":[{"id":"https://openalex.org/I4391767858","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyou Chai","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756","https://openalex.org/I4391767858"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["UTA Research Institute, The University of Texas at Arlington, Fort Worth, TX, USA","UTA Research Institute, University of Texas at Arlington, Fort Worth, TX, USA"],"affiliations":[{"raw_affiliation_string":"UTA Research Institute, The University of Texas at Arlington, Fort Worth, TX, USA","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"UTA Research Institute, University of Texas at Arlington, Fort Worth, TX, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100396295"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":4.26,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94397058,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"70","issue":"12","first_page":"8000","last_page":"8015"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.906499981880188,"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":0.906499981880188,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.774043083190918},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5351071953773499},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5133451819419861},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4814264476299286},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3680509328842163},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.32944124937057495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32069456577301025}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.774043083190918},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5351071953773499},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5133451819419861},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4814264476299286},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3680509328842163},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.32944124937057495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32069456577301025}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2025.3582529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3582529","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2380909745","display_name":null,"funder_award_id":"XLYC2403177","funder_id":"https://openalex.org/F4320329895","funder_display_name":"Liaoning Revitalization Talents Program"},{"id":"https://openalex.org/G2560105924","display_name":null,"funder_award_id":"62503187","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3316198426","display_name":null,"funder_award_id":"62394342","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3363996767","display_name":null,"funder_award_id":"62521001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3719319310","display_name":null,"funder_award_id":"62373090","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5620550699","display_name":null,"funder_award_id":"2023JH26/10200011","funder_id":"https://openalex.org/F4320336742","funder_display_name":"Key Research and Development Program of Liaoning Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329895","display_name":"Liaoning Revitalization Talents Program","ror":null},{"id":"https://openalex.org/F4320336742","display_name":"Key Research and Development Program of Liaoning Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1489014055","https://openalex.org/W1975886034","https://openalex.org/W1996927847","https://openalex.org/W2005437559","https://openalex.org/W2019338681","https://openalex.org/W2037864725","https://openalex.org/W2042106612","https://openalex.org/W2048153718","https://openalex.org/W2107675445","https://openalex.org/W2109640889","https://openalex.org/W2132917374","https://openalex.org/W2139416664","https://openalex.org/W2152161277","https://openalex.org/W2164522996","https://openalex.org/W2333120204","https://openalex.org/W2498694880","https://openalex.org/W2580629550","https://openalex.org/W2771641782","https://openalex.org/W2807176303","https://openalex.org/W2898645275","https://openalex.org/W2982527115","https://openalex.org/W2983464671","https://openalex.org/W3049644873","https://openalex.org/W3087896133","https://openalex.org/W3138463803","https://openalex.org/W4283319673","https://openalex.org/W4311909242","https://openalex.org/W4327808590","https://openalex.org/W4387903187","https://openalex.org/W4389232974","https://openalex.org/W4395689166","https://openalex.org/W4396713013","https://openalex.org/W4396817514","https://openalex.org/W4401507514"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"an":[3,39],"adaptive":[4],"discrete-time":[5],"linear":[6],"<inline-formula":[7],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[8],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[9],"notation=\"LaTeX\">$H_\\infty$</tex-math></inline-formula>":[10],"control":[11,42,154],"problem":[12,19,34],"with":[13],"networked":[14],"induced":[15],"dropouts.":[16],"First,":[17],"such":[18,89,176],"is":[20,29,179],"formulated":[21,33],"as":[22,118],"a":[23,45,58,147,166],"zero-sum":[24],"game":[25,60],"problem,":[26],"and":[27,44,75,104,111,132,156],"it":[28],"shown":[30],"that":[31],"the":[32,66,69,71,76,81,92,140,152,157,172,188,191],"can":[35],"be":[36],"solved":[37],"via":[38,143],"optimal":[40,153],"feedback":[41],"policy":[43,101,155,160],"worst":[46,158],"disturbance":[47,77,159],"policy.":[48],"These":[49],"policies":[50],"result":[51],"from":[52],"one":[53],"positive":[54],"definite":[55],"solution":[56,90],"to":[57,91,186],"modified":[59],"algebraic":[61],"Riccati":[62],"equation":[63],"(MGARE).":[64],"Then,":[65],"solvability":[67],"of":[68,80,175,190],"MGARE,":[70,93],"stochastic":[72],"asymptotical":[73],"stability":[74],"attenuation":[78],"level":[79],"closed-loop":[82],"system":[83],"are":[84,109,116,135,161,184],"rigorously":[85],"analyzed.":[86],"To":[87],"obtain":[88],"two":[94,125],"model-based":[95,122],"reinforcement":[96],"learning":[97],"(RL)":[98],"algorithms,":[99,108,124,128,134],"namely,":[100,129],"iteration":[102,106],"(PI)":[103],"value":[105],"(VI)":[107],"proposed":[110,192],"their":[112],"corresponding":[113],"convergence":[114],"analysis":[115],"given":[117,185],"well.":[119],"Based":[120],"on":[121],"RL":[123,127],"data-driven":[126,130,167],"PI":[131],"VI":[133],"designed":[136],"by":[137],"directly":[138],"using":[139],"data":[141],"transmitted":[142],"communication":[144],"networks":[145],"in":[146,150],"model-free":[148],"sense,":[149],"which":[151],"thus":[162],"obtained":[163],"iteratively.":[164],"Furthermore,":[165],"computation":[168],"algorithm":[169],"for":[170],"drawing":[171],"feasible":[173],"area":[174],"MGARE":[177],"approximately":[178],"designed.":[180],"Finally,":[181],"simulation":[182],"examples":[183],"show":[187],"effectiveness":[189],"approaches.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}