{"id":"https://openalex.org/W4410949604","doi":"https://doi.org/10.1109/tac.2025.3575649","title":"Policy Evaluation in Distributional LQR","display_name":"Policy Evaluation in Distributional LQR","publication_year":2025,"publication_date":"2025-06-02","ids":{"openalex":"https://openalex.org/W4410949604","doi":"https://doi.org/10.1109/tac.2025.3575649"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2025.3575649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3575649","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/A5059255896","display_name":"Zifan Wang","orcid":"https://orcid.org/0000-0001-6464-492X"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Zifan Wang","raw_affiliation_strings":["Division of Decision and Control Systems, School of Electrical Enginnering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden","Division of Decision and Control Systems, School of Electrical Enginnering and Computer ScienceKTH Royal Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Division of Decision and Control Systems, School of Electrical Enginnering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Decision and Control Systems, School of Electrical Enginnering and Computer ScienceKTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012777183","display_name":"Yulong Gao","orcid":"https://orcid.org/0000-0003-2338-5487"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yulong Gao","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Imperial College London, London, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, London, U.K","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104683060","display_name":"Siyi Wang","orcid":"https://orcid.org/0000-0003-1146-2473"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Siyi Wang","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080808780","display_name":"Michael M. Zavlanos","orcid":"https://orcid.org/0000-0003-1748-8228"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael M. Zavlanos","raw_affiliation_strings":["Department of Mechanical Engineering and Materials Science, Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering and Materials Science, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091718585","display_name":"Alessandro Abate","orcid":"https://orcid.org/0000-0002-5627-9093"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alessandro Abate","raw_affiliation_strings":["Department of Computer Science, University of Oxford, Oxford, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045975901","display_name":"Karl Henrik Johansson","orcid":"https://orcid.org/0000-0001-9940-5929"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Karl H. Johansson","raw_affiliation_strings":["Division of Decision and Control Systems, School of Electrical Enginnering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden","Division of Decision and Control Systems, School of Electrical Enginnering and Computer ScienceKTH Royal Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Division of Decision and Control Systems, School of Electrical Enginnering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Decision and Control Systems, School of Electrical Enginnering and Computer ScienceKTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5059255896"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":1.1617,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78363303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"70","issue":"11","first_page":"7477","last_page":"7492"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.3310999870300293,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.3310999870300293,"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/control-theory","display_name":"Control theory (sociology)","score":0.5656570196151733},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4444623291492462},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37644270062446594},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.32822930812835693},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3203410506248474},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.30063992738723755},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.26730579137802124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14690667390823364}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5656570196151733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4444623291492462},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37644270062446594},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.32822930812835693},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3203410506248474},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.30063992738723755},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26730579137802124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14690667390823364}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2025.3575649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3575649","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/G1257962346","display_name":null,"funder_award_id":"#FA9550-19-1-0169","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1855555568","https://openalex.org/W2128870461","https://openalex.org/W2765302304","https://openalex.org/W2822752092","https://openalex.org/W2905838893","https://openalex.org/W2947981406","https://openalex.org/W2966348706","https://openalex.org/W3119327948","https://openalex.org/W3129730011","https://openalex.org/W3171359374","https://openalex.org/W3179660843","https://openalex.org/W3213818741","https://openalex.org/W3215494060","https://openalex.org/W4205770363","https://openalex.org/W4206485356","https://openalex.org/W4210704481","https://openalex.org/W4289823579","https://openalex.org/W4311209065","https://openalex.org/W4322729780","https://openalex.org/W4395680534","https://openalex.org/W4406676273","https://openalex.org/W4410949604"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027","https://openalex.org/W2962838298","https://openalex.org/W2600246793"],"abstract_inverted_index":{"Distributional":[0],"reinforcement":[1,34],"learning":[2],"(DRL)":[3],"enhances":[4],"the":[5,8,11,14,20,43,49,52,69,98,101,126,129,135,139,147,150,157,196,207,231],"understanding":[6],"of":[7,10,22,51,72,100,110,128,138,149,163,181],"effects":[9],"randomness":[12],"in":[13,32,39],"environment":[15],"by":[16,177,211],"letting":[17],"agents":[18],"learn":[19],"distribution":[21,99,152,161,172],"a":[23,37,78,94,178,202],"random":[24,102,130,166,182],"return,":[25,103],"rather":[26],"than":[27],"its":[28],"expected":[29],"value":[30],"as":[31,113,115],"standard":[33],"learning.":[35],"Meanwhile,":[36],"challenge":[38,67],"DRL":[40,73],"is":[41,105,117,132,142,198],"that":[42,75,125,170],"policy":[44],"evaluation":[45],"typically":[46],"relies":[47],"on":[48,77],"representation":[50],"return":[53,131,151,160,208],"distribution,":[54,209],"which":[55,84,104],"needs":[56],"to":[57,153,220,229],"be":[58,174,189],"carefully":[59],"designed.":[60],"In":[61],"this":[62,66,171],"paper,":[63],"we":[64,85,92,145,168,200,216],"address":[65],"for":[68,97,107,205],"special":[70],"class":[71],"problems":[74],"rely":[76],"discounted":[79],"linear":[80,223],"quadratic":[81],"regulator":[82],"(LQR),":[83],"call":[86],"<italic":[87],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[88],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">distributional":[89],"LQR</i>.":[90],"Specifically,":[91],"provide":[93],"closed-form":[95],"expression":[96],"applicable":[106],"all":[108],"types":[109],"exogenous":[111,140],"disturbance":[112,141],"long":[114],"it":[116],"independent":[118],"and":[119],"identically":[120],"distributed":[121],"(i.i.d.).":[122],"We":[123],"show":[124,169],"variance":[127],"bounded":[133,191],"if":[134],"fourth":[136],"moment":[137],"bounded.":[143],"Furthermore,":[144],"investigate":[146],"sensitivity":[148],"model":[154,197],"perturbations.":[155],"While":[156],"proposed":[158],"exact":[159],"consists":[162],"infinitely":[164],"many":[165],"variables,":[167],"can":[173,188],"well":[175],"approximated":[176],"finite":[179],"number":[180],"variables.":[183],"The":[184],"associated":[185],"approximation":[186],"error":[187],"analytically":[190],"under":[192],"mild":[193],"assumptions.":[194],"When":[195],"unknown,":[199],"propose":[201],"model-free":[203],"approach":[204,219],"estimating":[206],"supported":[210],"sample":[212],"complexity":[213],"guarantees.":[214],"Finally,":[215],"extend":[217],"our":[218],"partially":[221],"observable":[222],"systems.":[224],"Numerical":[225],"experiments":[226],"are":[227],"provided":[228],"illustrate":[230],"theoretical":[232],"results.":[233]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}