{"id":"https://openalex.org/W3098412154","doi":"https://doi.org/10.1109/tac.2020.3037046","title":"Learning Optimal Controllers for Linear Systems With Multiplicative Noise via Policy Gradient","display_name":"Learning Optimal Controllers for Linear Systems With Multiplicative Noise via Policy Gradient","publication_year":2020,"publication_date":"2020-11-10","ids":{"openalex":"https://openalex.org/W3098412154","doi":"https://doi.org/10.1109/tac.2020.3037046","mag":"3098412154"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2020.3037046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2020.3037046","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":true,"oa_status":"green","oa_url":"https://repository.tudelft.nl/file/File_25def020-7c22-4737-b5b7-661e54d56f6f","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047397533","display_name":"Benjamin Gravell","orcid":"https://orcid.org/0000-0003-3302-0166"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Gravell","raw_affiliation_strings":["Control, Optimization, and Networks Lab., The University of Texas at Dallas, Richardson, TX 75080 USA"],"raw_orcid":"https://orcid.org/0000-0003-3302-0166","affiliations":[{"raw_affiliation_string":"Control, Optimization, and Networks Lab., The University of Texas at Dallas, Richardson, TX 75080 USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034611919","display_name":"Peyman Mohajerin Esfahani","orcid":"https://orcid.org/0000-0003-1286-8782"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Peyman Mohajerin Esfahani","raw_affiliation_strings":["Delft Center for Systems and Control, TU Delft, 2628 CD Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, TU Delft, 2628 CD Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051772147","display_name":"Tyler Summers","orcid":"https://orcid.org/0000-0002-0113-8912"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tyler Summers","raw_affiliation_strings":["Control, Optimization, and Networks Lab., The University of Texas at Dallas, Richardson, TX 75080 USA"],"raw_orcid":"https://orcid.org/0000-0002-0113-8912","affiliations":[{"raw_affiliation_string":"Control, Optimization, and Networks Lab., The University of Texas at Dallas, Richardson, TX 75080 USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4381,"has_fulltext":true,"cited_by_count":79,"citation_normalized_percentile":{"value":0.95509799,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"66","issue":"11","first_page":"5283","last_page":"5298"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9962000250816345,"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/T10046","display_name":"Stability and Control of Uncertain Systems","score":0.983299970626831,"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/multiplicative-noise","display_name":"Multiplicative noise","score":0.6899642944335938},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6867995262145996},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6631442308425903},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.5891550779342651},{"id":"https://openalex.org/keywords/multiplicative-function","display_name":"Multiplicative function","score":0.585693895816803},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5597580075263977},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5165366530418396},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.43180084228515625},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3221595585346222},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.31080347299575806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25202828645706177},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.0909636914730072}],"concepts":[{"id":"https://openalex.org/C18015164","wikidata":"https://www.wikidata.org/wiki/Q6935000","display_name":"Multiplicative noise","level":5,"score":0.6899642944335938},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6867995262145996},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6631442308425903},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.5891550779342651},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.585693895816803},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5597580075263977},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5165366530418396},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.43180084228515625},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3221595585346222},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31080347299575806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25202828645706177},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.0909636914730072},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C131021393","wikidata":"https://www.wikidata.org/wiki/Q7512759","display_name":"Signal transfer function","level":4,"score":0.0},{"id":"https://openalex.org/C13412647","wikidata":"https://www.wikidata.org/wiki/Q174948","display_name":"Analog signal","level":3,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tac.2020.3037046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2020.3037046","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"},{"id":"pmh:oai:tudelft.nl:uuid:aecd5a3d-d429-4433-9fe3-13080316fd05","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:aecd5a3d-d429-4433-9fe3-13080316fd05","pdf_url":"https://repository.tudelft.nl/file/File_25def020-7c22-4737-b5b7-661e54d56f6f","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"}],"best_oa_location":{"id":"pmh:oai:tudelft.nl:uuid:aecd5a3d-d429-4433-9fe3-13080316fd05","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:aecd5a3d-d429-4433-9fe3-13080316fd05","pdf_url":"https://repository.tudelft.nl/file/File_25def020-7c22-4737-b5b7-661e54d56f6f","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"},"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G240356698","display_name":null,"funder_award_id":"W911NF-17-1-0058","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8059218201","display_name":null,"funder_award_id":"FA2386-19-1-4073","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3098412154.pdf","grobid_xml":"https://content.openalex.org/works/W3098412154.grobid-xml"},"referenced_works_count":78,"referenced_works":["https://openalex.org/W53582479","https://openalex.org/W651734400","https://openalex.org/W1582653889","https://openalex.org/W1616818660","https://openalex.org/W1975498076","https://openalex.org/W1981042292","https://openalex.org/W1981066143","https://openalex.org/W1990139897","https://openalex.org/W1995502176","https://openalex.org/W2002858896","https://openalex.org/W2004001705","https://openalex.org/W2011866373","https://openalex.org/W2022611390","https://openalex.org/W2052334067","https://openalex.org/W2055140741","https://openalex.org/W2082210980","https://openalex.org/W2098432798","https://openalex.org/W2107411554","https://openalex.org/W2120871244","https://openalex.org/W2123486671","https://openalex.org/W2124783336","https://openalex.org/W2127107099","https://openalex.org/W2129488707","https://openalex.org/W2130801532","https://openalex.org/W2145339207","https://openalex.org/W2152161277","https://openalex.org/W2153292828","https://openalex.org/W2153461933","https://openalex.org/W2163083887","https://openalex.org/W2168090960","https://openalex.org/W2275844880","https://openalex.org/W2395955964","https://openalex.org/W2590144118","https://openalex.org/W2605102758","https://openalex.org/W2761923184","https://openalex.org/W2804569092","https://openalex.org/W2807098429","https://openalex.org/W2822752092","https://openalex.org/W2854640194","https://openalex.org/W2886474253","https://openalex.org/W2888916820","https://openalex.org/W2902907165","https://openalex.org/W2916346876","https://openalex.org/W2943040161","https://openalex.org/W2946924892","https://openalex.org/W2963248893","https://openalex.org/W2963400148","https://openalex.org/W2963774238","https://openalex.org/W2964084913","https://openalex.org/W2966348706","https://openalex.org/W2972533062","https://openalex.org/W3006596960","https://openalex.org/W3012118400","https://openalex.org/W3012546009","https://openalex.org/W3045891384","https://openalex.org/W3046017196","https://openalex.org/W3098045837","https://openalex.org/W3098788257","https://openalex.org/W3156973010","https://openalex.org/W3210839039","https://openalex.org/W4250589301","https://openalex.org/W4288346974","https://openalex.org/W6651597697","https://openalex.org/W6679257226","https://openalex.org/W6681861716","https://openalex.org/W6683656826","https://openalex.org/W6726004062","https://openalex.org/W6745072325","https://openalex.org/W6746722099","https://openalex.org/W6751494857","https://openalex.org/W6752522973","https://openalex.org/W6754297394","https://openalex.org/W6755717975","https://openalex.org/W6759659934","https://openalex.org/W6766686101","https://openalex.org/W6776220230","https://openalex.org/W6784745534","https://openalex.org/W6841713301"],"related_works":["https://openalex.org/W4318195686","https://openalex.org/W2975999359","https://openalex.org/W3022718941","https://openalex.org/W4287812451","https://openalex.org/W2506602630","https://openalex.org/W1996414039","https://openalex.org/W3097284316","https://openalex.org/W2332961228","https://openalex.org/W2203843426","https://openalex.org/W2049369111"],"abstract_inverted_index":{"The":[0],"linear":[1],"quadratic":[2],"regulator":[3],"(LQR)":[4],"problem":[5,171],"has":[6,140],"reemerged":[7],"as":[8,110],"an":[9],"important":[10],"theoretical":[11],"benchmark":[12],"for":[13,83],"reinforcement":[14,75],"learning-based":[15],"control":[16,165],"of":[17,63,99,108,127,157,185],"complex":[18],"dynamical":[19],"systems":[20],"with":[21,29,167],"continuous":[22],"state":[23],"and":[24,52,58,70,180],"action":[25],"spaces.":[26],"In":[27],"contrast":[28],"nearly":[30],"all":[31],"recent":[32],"work":[33,117],"in":[34,54,74,112,177],"this":[35],"area,":[36],"we":[37,132],"consider":[38],"multiplicative":[39,100,136],"noise":[40,101,137],"models,":[41],"which":[42,79,150],"are":[43,174,188],"increasingly":[44],"relevant":[45],"because":[46],"they":[47],"explicitly":[48],"incorporate":[49],"inherent":[50],"uncertainty":[51,84],"variation":[53],"the":[55,64,135,162,178],"system":[56,186],"dynamics":[57],"thereby":[59],"improve":[60],"robustness":[61,107],"properties":[62],"controller.":[65],"Robustness":[66],"is":[67,151],"a":[68,128,141],"critical":[69],"poorly":[71],"understood":[72],"issue":[73],"learning;":[76],"existing":[77],"methods":[78],"do":[80],"not":[81],"account":[82],"can":[85,105],"converge":[86,93],"to":[87,92,153,161,190],"fragile":[88],"policies":[89],"or":[90],"fail":[91],"at":[94],"all.":[95],"Additionally,":[96],"intentional":[97],"injection":[98],"into":[102],"learning":[103],"algorithms":[104,124,160],"enhance":[106],"policies,":[109],"observed":[111],"<italic":[113,145],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[114,146],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">ad":[115],"hoc</i>":[116],"on":[118,170],"domain":[119],"randomization.":[120],"Although":[121],"policy":[122,158,166,192],"gradient":[123,159],"require":[125],"optimization":[126],"nonconvex":[129],"cost":[130,139],"function,":[131],"show":[133],"that":[134],"LQR":[138],"special":[142],"property":[143],"called":[144],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">gradient":[147],"domination</i>":[148],",":[149],"exploited":[152],"prove":[154],"global":[155],"convergence":[156],"globally":[163],"optimum":[164],"polynomial":[168],"dependence":[169],"parameters.":[172],"Results":[173],"provided":[175],"both":[176],"model-known":[179],"model-unknown":[181],"settings":[182],"where":[183],"samples":[184],"trajectories":[187],"used":[189],"estimate":[191],"gradients":[193]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":26},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}