{"id":"https://openalex.org/W4413319008","doi":"https://doi.org/10.1109/tnnls.2025.3593259","title":"Information-State-Based Reinforcement Learning for the Control of Partially Observed Nonlinear Systems","display_name":"Information-State-Based Reinforcement Learning for the Control of Partially Observed Nonlinear Systems","publication_year":2025,"publication_date":"2025-08-19","ids":{"openalex":"https://openalex.org/W4413319008","doi":"https://doi.org/10.1109/tnnls.2025.3593259","pmid":"https://pubmed.ncbi.nlm.nih.gov/40828720"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3593259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3593259","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5072338368","display_name":"Raman Goyal","orcid":"https://orcid.org/0000-0002-8128-3051"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Raman Goyal","raw_affiliation_strings":["Department of Aerospace Engineering, Texas A&M University, College Station, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-8128-3051","affiliations":[{"raw_affiliation_string":"Department of Aerospace Engineering, Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090447176","display_name":"Mohamed Naveed Gul Mohamed","orcid":"https://orcid.org/0000-0001-5718-2261"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohamed Naveed Gul Mohamed","raw_affiliation_strings":["Department of Aerospace Engineering, Texas A&M University, College Station, TX, USA"],"raw_orcid":"https://orcid.org/0000-0001-5718-2261","affiliations":[{"raw_affiliation_string":"Department of Aerospace Engineering, Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062133226","display_name":"Ran Wang","orcid":"https://orcid.org/0000-0003-1698-5978"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ran Wang","raw_affiliation_strings":["Department of Aerospace Engineering, Texas A&M University, College Station, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-1698-5978","affiliations":[{"raw_affiliation_string":"Department of Aerospace Engineering, Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078202724","display_name":"Aayushman Sharma","orcid":null},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aayushman Sharma","raw_affiliation_strings":["Department of Aerospace Engineering, Texas A&M University, College Station, TX, USA"],"raw_orcid":"https://orcid.org/0009-0004-6481-8968","affiliations":[{"raw_affiliation_string":"Department of Aerospace Engineering, Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":null,"display_name":"Suman Chakravorty","orcid":"https://orcid.org/0000-0003-1598-5060"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suman Chakravorty","raw_affiliation_strings":["Department of Aerospace Engineering, Texas A&M University, College Station, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-1598-5060","affiliations":[{"raw_affiliation_string":"Department of Aerospace Engineering, Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5072338368"],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24097595,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"12","first_page":"20386","last_page":"20400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14083","display_name":"Extremum Seeking Control Systems","score":0.9666000008583069,"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"}},"topics":[{"id":"https://openalex.org/T14083","display_name":"Extremum Seeking Control Systems","score":0.9666000008583069,"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"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9526000022888184,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.941100001335144,"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":0.687143087387085},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5896390676498413},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.578216552734375},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5721668004989624},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5484784245491028},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.448154091835022},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3983120620250702},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32889580726623535},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2398325502872467},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.14027386903762817},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13617423176765442},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07230615615844727}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.687143087387085},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5896390676498413},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.578216552734375},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5721668004989624},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5484784245491028},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.448154091835022},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3983120620250702},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32889580726623535},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2398325502872467},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.14027386903762817},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13617423176765442},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07230615615844727},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3593259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3593259","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:40828720","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40828720","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1662842982","https://openalex.org/W2066557929","https://openalex.org/W2087617385","https://openalex.org/W2100563249","https://openalex.org/W2151966330","https://openalex.org/W2158782408","https://openalex.org/W2167856595","https://openalex.org/W2484646121","https://openalex.org/W2754517384","https://openalex.org/W3044661254","https://openalex.org/W3047319512","https://openalex.org/W3127275112","https://openalex.org/W3198733989","https://openalex.org/W3204719635","https://openalex.org/W3206375218","https://openalex.org/W4200140111","https://openalex.org/W4210250498","https://openalex.org/W4297964528","https://openalex.org/W4313614005","https://openalex.org/W4322706663","https://openalex.org/W4382935641","https://openalex.org/W4385453470","https://openalex.org/W4391020128","https://openalex.org/W4391021839","https://openalex.org/W4399570217","https://openalex.org/W4399978440","https://openalex.org/W4410431980","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"This":[0,123],"article":[1],"develops":[2],"a":[3,18,36,82,100,129],"model-based":[4],"reinforcement":[5],"learning":[6],"(RL)":[7],"approach":[8,27,124],"to":[9,28,73,127,140],"the":[10,31,41,46,56,59,62,71,76,86,93,106,120,141,151,164],"closed-loop":[11],"control":[12,51,67,133],"of":[13,45,58,85,95,105,150,166],"nonlinear":[14,20,160],"dynamical":[15,161],"systems":[16,98,162],"with":[17],"partial":[19],"observation":[21],"model.":[22],"We":[23,53,80],"propose":[24],"an":[25,111,137],"\"information-state\"-based":[26],"rigorously":[29],"transform":[30],"partially":[32,64,96,142],"observed":[33,38,65,97,143],"problem":[34,39,146],"into":[35],"fully":[37],"where":[40],"information":[42],"state":[43],"consists":[44],"past":[47],"several":[48],"observations":[49],"and":[50,61,69,168],"inputs.":[52],"further":[54],"show":[55],"equivalence":[57],"transformed":[60],"initial":[63],"optimal":[66,78],"problems":[68],"provide":[70],"conditions":[72],"solve":[74],"for":[75,92],"deterministic":[77],"solution.":[79],"develop":[81],"data-based":[83],"generalization":[84],"iterative":[87],"linear":[88,102],"quadratic":[89],"regulator":[90],"(ILQR)":[91],"RL":[94],"using":[99,118],"local":[101,130],"time-varying":[103],"model":[104,114,167],"information-state":[107],"dynamics":[108],"approximated":[109],"by":[110,156],"autoregressive-moving-average":[112],"(ARMA)":[113],"that":[115,135],"is":[116,154],"generated":[117],"only":[119],"input-output":[121],"data.":[122],"allows":[125],"us":[126],"design":[128,145],"perturbation":[131],"feedback":[132,144],"law":[134],"provides":[136],"optimum":[138],"solution":[139],"locally.":[147],"The":[148],"efficacy":[149],"developed":[152],"method":[153],"shown":[155],"controlling":[157],"complex":[158],"high-dimensional":[159],"in":[163],"presence":[165],"sensing":[169],"uncertainty.":[170]},"counts_by_year":[],"updated_date":"2025-12-03T23:09:05.601824","created_date":"2025-10-10T00:00:00"}