{"id":"https://openalex.org/W4396713013","doi":"https://doi.org/10.1109/tac.2024.3397928","title":"Robust Reinforcement Learning for Risk-Sensitive Linear Quadratic Gaussian Control","display_name":"Robust Reinforcement Learning for Risk-Sensitive Linear Quadratic Gaussian Control","publication_year":2024,"publication_date":"2024-05-07","ids":{"openalex":"https://openalex.org/W4396713013","doi":"https://doi.org/10.1109/tac.2024.3397928"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2024.3397928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2024.3397928","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/A5062455237","display_name":"Leilei Cui","orcid":"https://orcid.org/0000-0001-8031-7638"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leilei Cui","raw_affiliation_strings":["Control and Networks Lab, Department of Electrical and Computer Engineering, Tandon School of Engineering, New York University, Brooklyn, NY, USA"],"raw_orcid":"https://orcid.org/0000-0001-8031-7638","affiliations":[{"raw_affiliation_string":"Control and Networks Lab, Department of Electrical and Computer Engineering, Tandon School of Engineering, New York University, Brooklyn, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019604570","display_name":"Tamer Ba\u015far","orcid":"https://orcid.org/0000-0003-4406-7875"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tamer Ba\u015far","raw_affiliation_strings":["Coordinated Science Laboratory, University of Illinois Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0000-0003-4406-7875","affiliations":[{"raw_affiliation_string":"Coordinated Science Laboratory, University of Illinois Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067046312","display_name":"Zhong\u2010Ping Jiang","orcid":"https://orcid.org/0000-0002-4868-9359"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong-Ping Jiang","raw_affiliation_strings":["Control and Networks Lab, Department of Electrical and Computer Engineering, Tandon School of Engineering, New York University, Brooklyn, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-4868-9359","affiliations":[{"raw_affiliation_string":"Control and Networks Lab, Department of Electrical and Computer Engineering, Tandon School of Engineering, New York University, Brooklyn, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.53,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.93006792,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"69","issue":"11","first_page":"7678","last_page":"7693"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9466999769210815,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9466999769210815,"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":0.9347000122070312,"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/T10046","display_name":"Stability and Control of Uncertain Systems","score":0.9343000054359436,"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/linear-quadratic-gaussian-control","display_name":"Linear-quadratic-Gaussian control","score":0.7532171010971069},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6189180612564087},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5592145919799805},{"id":"https://openalex.org/keywords/robust-control","display_name":"Robust control","score":0.5111520886421204},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4573393166065216},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.4561059772968292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4550902843475342},{"id":"https://openalex.org/keywords/linear-control-systems","display_name":"Linear control systems","score":0.454723984003067},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.43530622124671936},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.39393773674964905},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3818357288837433},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.37952953577041626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34997260570526123},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34279581904411316},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.2983466386795044},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1848360300064087},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.0667603611946106},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0653243362903595}],"concepts":[{"id":"https://openalex.org/C204495892","wikidata":"https://www.wikidata.org/wiki/Q1798304","display_name":"Linear-quadratic-Gaussian control","level":3,"score":0.7532171010971069},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6189180612564087},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5592145919799805},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.5111520886421204},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4573393166065216},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4561059772968292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4550902843475342},{"id":"https://openalex.org/C2987686001","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Linear control systems","level":3,"score":0.454723984003067},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.43530622124671936},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39393773674964905},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3818357288837433},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.37952953577041626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34997260570526123},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34279581904411316},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2983466386795044},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1848360300064087},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0667603611946106},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0653243362903595},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2024.3397928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2024.3397928","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":[{"id":"https://metadata.un.org/sdg/16","score":0.7200000286102295,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W55814457","https://openalex.org/W83533993","https://openalex.org/W560518094","https://openalex.org/W638400246","https://openalex.org/W2004470537","https://openalex.org/W2005437559","https://openalex.org/W2011866373","https://openalex.org/W2027591506","https://openalex.org/W2037025184","https://openalex.org/W2038137192","https://openalex.org/W2065313971","https://openalex.org/W2096035449","https://openalex.org/W2097521761","https://openalex.org/W2102295697","https://openalex.org/W2106929622","https://openalex.org/W2116479681","https://openalex.org/W2120038868","https://openalex.org/W2139418546","https://openalex.org/W2142717543","https://openalex.org/W2167168611","https://openalex.org/W2484646121","https://openalex.org/W2896663787","https://openalex.org/W2947577977","https://openalex.org/W2984078320","https://openalex.org/W3098412154","https://openalex.org/W3100975812","https://openalex.org/W3111531580","https://openalex.org/W3158964610","https://openalex.org/W3166923021","https://openalex.org/W3172934943","https://openalex.org/W3175769301","https://openalex.org/W3209135762","https://openalex.org/W3212753778","https://openalex.org/W3213818741","https://openalex.org/W4200563642","https://openalex.org/W4205326910","https://openalex.org/W4214717370","https://openalex.org/W4220681550","https://openalex.org/W4233696721","https://openalex.org/W4234350010","https://openalex.org/W4254127125","https://openalex.org/W4301886962","https://openalex.org/W4396527639","https://openalex.org/W4396713013","https://openalex.org/W6754297394","https://openalex.org/W6762982123","https://openalex.org/W6770404689","https://openalex.org/W6785420126","https://openalex.org/W6787869850","https://openalex.org/W6847076449"],"related_works":["https://openalex.org/W2047558453","https://openalex.org/W1986869206","https://openalex.org/W2523371140","https://openalex.org/W1999673819","https://openalex.org/W958199350","https://openalex.org/W4238753042","https://openalex.org/W2380695172","https://openalex.org/W1573796078","https://openalex.org/W2105827667","https://openalex.org/W2072340177"],"abstract_inverted_index":{"This":[0,79],"paper":[1],"proposes":[2],"a":[3,45,54,97,124],"novel":[4,125],"robust":[5,55,72],"reinforcement":[6],"learning":[7,77,111],"framework":[8],"for":[9],"discrete-time":[10],"linear":[11,41],"systems":[12],"with":[13],"model":[14],"mismatch":[15],"that":[16,89],"may":[17],"arise":[18],"from":[19,31],"the":[20,35,38,76,90,101,107,119,140],"sim-to-real":[21],"gap.":[22],"A":[23],"key":[24],"strategy":[25],"is":[26,50,63,82,113,122,131],"to":[27,52,65,96,138],"invoke":[28],"advanced":[29],"techniques":[30],"control":[32],"theory.":[33],"Using":[34],"formulation":[36],"of":[37,100],"classical":[39],"risk-sensitive":[40],"quadratic":[42],"Gaussian":[43],"control,":[44],"dual-loop":[46,59],"policy":[47,60,92,128],"optimization":[48,61,93,129],"algorithm":[49,62,94,130],"proposed":[51,91,141],"generate":[53],"optimal":[56,102],"controller.":[57],"The":[58],"shown":[64],"be":[66],"globally":[67],"and":[68,71,87],"uniformly":[69],"convergent,":[70],"against":[73],"disturbances":[74],"during":[75],"process.":[78],"robustness":[80],"property":[81],"called":[83],"small-disturbance":[84],"input-to-state":[85],"stability":[86],"guarantees":[88],"converges":[95],"small":[98],"neighborhood":[99],"controller":[103],"as":[104,106],"long":[105],"disturbance":[108],"at":[109],"each":[110],"step":[112],"relatively":[114],"small.":[115],"In":[116],"addition,":[117],"when":[118],"system":[120],"dynamics":[121],"unknown,":[123],"model-free":[126],"off-policy":[127],"proposed.":[132],"Finally,":[133],"numerical":[134],"examples":[135],"are":[136],"provided":[137],"illustrate":[139],"algorithm.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}