{"id":"https://openalex.org/W2573470024","doi":"https://doi.org/10.1109/tac.2017.2653942","title":"Thompson Sampling for Stochastic Control: The Finite Parameter Case","display_name":"Thompson Sampling for Stochastic Control: The Finite Parameter Case","publication_year":2017,"publication_date":"2017-01-16","ids":{"openalex":"https://openalex.org/W2573470024","doi":"https://doi.org/10.1109/tac.2017.2653942","mag":"2573470024"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2017.2653942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2017.2653942","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/A5067589334","display_name":"Michael Jong Kim","orcid":"https://orcid.org/0000-0002-1858-4142"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Michael Jong Kim","raw_affiliation_strings":["Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5067589334"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":15.4995,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":{"value":0.99180109,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"62","issue":"12","first_page":"6415","last_page":"6422"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11773","display_name":"Healthcare Operations and Scheduling Optimization","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/3604","display_name":"Emergency Medical Services"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10067","display_name":"Stochastic processes and financial applications","score":0.9858999848365784,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.7497525215148926},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.7098926901817322},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6355697512626648},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.6021084189414978},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5083975195884705},{"id":"https://openalex.org/keywords/parameter-space","display_name":"Parameter space","score":0.4942922592163086},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4826217591762543},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4761538505554199},{"id":"https://openalex.org/keywords/finite-set","display_name":"Finite set","score":0.4418204724788666},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.43236973881721497},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.42592161893844604},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.38296592235565186},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.313509464263916},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.2885507047176361},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.26880741119384766},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17849811911582947},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.14639335870742798},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11427783966064453}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7497525215148926},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.7098926901817322},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6355697512626648},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6021084189414978},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5083975195884705},{"id":"https://openalex.org/C73586568","wikidata":"https://www.wikidata.org/wiki/Q2600211","display_name":"Parameter space","level":2,"score":0.4942922592163086},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4826217591762543},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4761538505554199},{"id":"https://openalex.org/C162392398","wikidata":"https://www.wikidata.org/wiki/Q272404","display_name":"Finite set","level":2,"score":0.4418204724788666},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.43236973881721497},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.42592161893844604},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38296592235565186},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.313509464263916},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.2885507047176361},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.26880741119384766},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17849811911582947},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.14639335870742798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11427783966064453},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2017.2653942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2017.2653942","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":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W203276351","https://openalex.org/W1498636830","https://openalex.org/W1561424154","https://openalex.org/W1571154989","https://openalex.org/W1601081659","https://openalex.org/W1731081199","https://openalex.org/W1911551976","https://openalex.org/W1973476981","https://openalex.org/W1975736346","https://openalex.org/W1979790576","https://openalex.org/W1982997797","https://openalex.org/W1995240981","https://openalex.org/W2013514814","https://openalex.org/W2032100464","https://openalex.org/W2039522160","https://openalex.org/W2064076655","https://openalex.org/W2068782949","https://openalex.org/W2076522620","https://openalex.org/W2091711926","https://openalex.org/W2111764152","https://openalex.org/W2118487768","https://openalex.org/W2124293649","https://openalex.org/W2125142970","https://openalex.org/W2125930088","https://openalex.org/W2142176084","https://openalex.org/W2327833721","https://openalex.org/W2502318419","https://openalex.org/W2949186496","https://openalex.org/W2962901934","https://openalex.org/W3106537191","https://openalex.org/W3145241921","https://openalex.org/W4245744559","https://openalex.org/W6633965395","https://openalex.org/W6639904974","https://openalex.org/W6676833704","https://openalex.org/W6786344146"],"related_works":["https://openalex.org/W4376155396","https://openalex.org/W2971351794","https://openalex.org/W1947085858","https://openalex.org/W2101991911","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2155070487","https://openalex.org/W185460758","https://openalex.org/W1586941005","https://openalex.org/W3161382554"],"abstract_inverted_index":{"In":[0],"this":[1,57],"paper,":[2],"we":[3,20],"apply":[4],"Thompson":[5,64],"sampling":[6,65],"to":[7],"a":[8,50,60,67],"class":[9],"of":[10,56,74],"average":[11,23,70],"reward":[12,24,36],"stochastic":[13,25],"control":[14,26],"problems":[15],"with":[16],"parameter":[17,46],"uncertainty.":[18],"Specifically,":[19],"study":[21],"an":[22,29,44],"problem":[27],"over":[28],"infinite":[30],"horizon":[31],"in":[32,49],"which":[33,80],"both":[34],"the":[35],"and":[37],"state":[38],"transition":[39],"distributions":[40],"are":[41],"parameterized":[42],"by":[43],"unknown":[45],"taking":[47],"values":[48],"finite":[51],"space.":[52],"The":[53],"main":[54],"result":[55],"paper":[58],"is":[59,81],"proof":[61],"showing":[62],"that":[63],"achieves":[66],"worst":[68],"case":[69],"per":[71],"period":[72],"regret":[73],"O(T":[75],"<sup":[76],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[77],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">-1</sup>":[78],"),":[79],"asymptotically":[82],"optimal.":[83]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":52},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}