{"id":"https://openalex.org/W4413393378","doi":"https://doi.org/10.23919/acc63710.2025.11107833","title":"A Reduced-Order Output Feedback Parameterization for Reinforcement Learning Control with Application to the LQR Problem","display_name":"A Reduced-Order Output Feedback Parameterization for Reinforcement Learning Control with Application to the LQR Problem","publication_year":2025,"publication_date":"2025-07-08","ids":{"openalex":"https://openalex.org/W4413393378","doi":"https://doi.org/10.23919/acc63710.2025.11107833"},"language":"en","primary_location":{"id":"doi:10.23919/acc63710.2025.11107833","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-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/A5023772121","display_name":"Syed Ali Asad Rizvi","orcid":"https://orcid.org/0000-0003-1412-8841"},"institutions":[{"id":"https://openalex.org/I63920570","display_name":"Tennessee Technological University","ror":"https://ror.org/05drmrq39","country_code":"US","type":"education","lineage":["https://openalex.org/I63920570"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Syed Ali Asad Rizvi","raw_affiliation_strings":["Tennessee Technological University,Department of Electrical and Computer Engineering,Cookeville,TN,USA,38505"],"affiliations":[{"raw_affiliation_string":"Tennessee Technological University,Department of Electrical and Computer Engineering,Cookeville,TN,USA,38505","institution_ids":["https://openalex.org/I63920570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072774939","display_name":"Zongli Lin","orcid":"https://orcid.org/0000-0003-1589-1443"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zongli Lin","raw_affiliation_strings":["University of Virginia,Charles L. Brown Department of Electrical and Computer Enigneering,Charlottesville,VA,22903"],"affiliations":[{"raw_affiliation_string":"University of Virginia,Charles L. Brown Department of Electrical and Computer Enigneering,Charlottesville,VA,22903","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5023772121"],"corresponding_institution_ids":["https://openalex.org/I63920570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32290322,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"218","last_page":"223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11749","display_name":"Iterative Learning Control Systems","score":0.9739999771118164,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.9739999771118164,"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":0.9023000001907349,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8168565034866333},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.7414762377738953},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5904229283332825},{"id":"https://openalex.org/keywords/feedback-control","display_name":"Feedback control","score":0.557867169380188},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5476129055023193},{"id":"https://openalex.org/keywords/output-feedback","display_name":"Output feedback","score":0.5469997525215149},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.4881154000759125},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3408637046813965},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20723119378089905},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16789773106575012}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8168565034866333},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7414762377738953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5904229283332825},{"id":"https://openalex.org/C3018651601","wikidata":"https://www.wikidata.org/wiki/Q183635","display_name":"Feedback control","level":2,"score":0.557867169380188},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5476129055023193},{"id":"https://openalex.org/C3018623182","wikidata":"https://www.wikidata.org/wiki/Q154021","display_name":"Output feedback","level":3,"score":0.5469997525215149},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.4881154000759125},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3408637046813965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20723119378089905},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16789773106575012}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc63710.2025.11107833","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1531602929","https://openalex.org/W1616818660","https://openalex.org/W1854776945","https://openalex.org/W2011866373","https://openalex.org/W2019338681","https://openalex.org/W2041626001","https://openalex.org/W2151966330","https://openalex.org/W2152161277","https://openalex.org/W2153890087","https://openalex.org/W2291165559","https://openalex.org/W2560131027","https://openalex.org/W2884356520","https://openalex.org/W2897702175","https://openalex.org/W4214717370","https://openalex.org/W4310121338","https://openalex.org/W4313122311","https://openalex.org/W4390120077"],"related_works":["https://openalex.org/W2607757002","https://openalex.org/W2334516743","https://openalex.org/W2486306719","https://openalex.org/W2106487132","https://openalex.org/W2369282358","https://openalex.org/W2482257683","https://openalex.org/W3022029778","https://openalex.org/W2019249007","https://openalex.org/W2800406697","https://openalex.org/W2139918612"],"abstract_inverted_index":{"Data-driven":[0],"reinforcement":[1,71],"learning":[2,45,59,72,108,163],"(RL)":[3],"algorithms":[4],"primarily":[5],"rely":[6],"on":[7,158],"the":[8,14,17,30,35,55,58,111,124,136,150,159,170,185,188],"system":[9],"data":[10],"that":[11,74,97,135],"may":[12],"take":[13],"input-state":[15,56],"or":[16],"input-output":[18,78],"form.":[19],"Input-output":[20],"form":[21],"is":[22,61,66,98,133,138,146,165,174],"preferred":[23],"by":[24],"controls":[25],"practitioners":[26],"as":[27,129],"it":[28],"relaxes":[29],"sensing":[31],"requirements":[32,86],"compared":[33,191],"to":[34,54,83,115,169,183,192],"full-state":[36],"feedback":[37,43,196],"case.":[38,152],"The":[39],"design":[40],"of":[41,69,119,187],"output":[42,195],"data-driven":[44],"techniques":[46],"is,":[47],"however,":[48],"a":[49,67,94,130],"challenging":[50],"control":[51,102,118,198],"problem.":[52],"Compared":[53],"form,":[57],"complexity":[60],"often":[62],"significantly":[63],"higher.":[64],"This":[65],"result":[68],"higher-order":[70],"equations":[73],"require":[75],"deep":[76],"historic":[77],"datasets,":[79],"which":[80],"then":[81],"translates":[82],"higher":[84],"exploration":[85],"and":[87],"increased":[88],"sample":[89],"complexity.":[90],"We":[91],"present":[92],"here":[93],"reduced-order":[95,106,161,189],"parameterization":[96,137],"tailored":[99],"for":[100],"RL-based":[101,116],"applications":[103],"towards":[104],"obtaining":[105],"RL":[107,197],"equations.":[109],"While":[110],"results":[112,180],"are":[113,181],"general":[114],"optimal":[117],"LTI":[120],"systems,":[121],"we":[122],"consider":[123],"classic":[125],"Q-learning":[126,155],"LQR":[127,172],"algorithm":[128,156],"proof-of-concept.":[131],"It":[132],"shown":[134,175],"exact":[139],"in":[140],"N":[141,145],"steps,":[142],"where":[143],"this":[144],"always":[147],"smaller":[148],"than":[149],"full-order":[151,194],"An":[153],"iterative":[154],"based":[157],"proposed":[160],"parameterized":[162],"equation":[164],"presented,":[166],"whose":[167],"convergence":[168],"nominal":[171],"solution":[173],"analytically.":[176],"Finally,":[177],"numerical":[178],"simulation":[179],"presented":[182],"show":[184],"effectiveness":[186],"method":[190],"existing":[193],"approaches.":[199]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}