{"id":"https://openalex.org/W2783297289","doi":"https://doi.org/10.1109/allerton.2017.8262873","title":"Control of unknown linear systems with Thompson sampling","display_name":"Control of unknown linear systems with Thompson sampling","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2783297289","doi":"https://doi.org/10.1109/allerton.2017.8262873","mag":"2783297289"},"language":"en","primary_location":{"id":"doi:10.1109/allerton.2017.8262873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2017.8262873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 55th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","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/A5100627878","display_name":"Yi Ouyang","orcid":"https://orcid.org/0000-0003-0556-4393"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yi Ouyang","raw_affiliation_strings":["EECS department, UC Berkeley"],"affiliations":[{"raw_affiliation_string":"EECS department, UC Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018463719","display_name":"Mukul Gagrani","orcid":"https://orcid.org/0000-0003-0483-1090"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mukul Gagrani","raw_affiliation_strings":["Department of Electrical Engineering, University of Southern California, Los Angeles"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Southern California, Los Angeles","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002082998","display_name":"Rahul Jain","orcid":"https://orcid.org/0000-0003-3786-8682"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahul Jain","raw_affiliation_strings":["Department of Electrical Engineering, University of Southern California, Los Angeles"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Southern California, Los Angeles","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100627878"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":7.2331,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.97220371,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1198","last_page":"1205"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"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":1.0,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9879999756813049,"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/T12288","display_name":"Optimization and Search Problems","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.8211364150047302},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.6650620102882385},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.6584065556526184},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.6163591146469116},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.5784226059913635},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.543079137802124},{"id":"https://openalex.org/keywords/stopping-time","display_name":"Stopping time","score":0.42982223629951477},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.4287635385990143},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.42539823055267334},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.42367786169052124},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.41365665197372437},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4135870337486267},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37813276052474976},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.353506863117218},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.35167521238327026},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.33773747086524963},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.30407679080963135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14041656255722046},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.10069486498832703}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8211364150047302},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.6650620102882385},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6584065556526184},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.6163591146469116},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.5784226059913635},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.543079137802124},{"id":"https://openalex.org/C99888217","wikidata":"https://www.wikidata.org/wiki/Q1288707","display_name":"Stopping time","level":2,"score":0.42982223629951477},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.4287635385990143},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.42539823055267334},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.42367786169052124},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.41365665197372437},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4135870337486267},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37813276052474976},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.353506863117218},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.35167521238327026},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.33773747086524963},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.30407679080963135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14041656255722046},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.10069486498832703},{"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/allerton.2017.8262873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2017.8262873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 55th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","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":37,"referenced_works":["https://openalex.org/W50486269","https://openalex.org/W53582479","https://openalex.org/W105751747","https://openalex.org/W1535136082","https://openalex.org/W1569320505","https://openalex.org/W1901083042","https://openalex.org/W1911551976","https://openalex.org/W1972484140","https://openalex.org/W2009551863","https://openalex.org/W2039522160","https://openalex.org/W2048287263","https://openalex.org/W2089667489","https://openalex.org/W2094826322","https://openalex.org/W2108738385","https://openalex.org/W2111764152","https://openalex.org/W2143253189","https://openalex.org/W2149721706","https://openalex.org/W2158125716","https://openalex.org/W2158319693","https://openalex.org/W2166074282","https://openalex.org/W2166253248","https://openalex.org/W2403303158","https://openalex.org/W2513739600","https://openalex.org/W2604209058","https://openalex.org/W2949186496","https://openalex.org/W2962861921","https://openalex.org/W2963603291","https://openalex.org/W4234228486","https://openalex.org/W4236323066","https://openalex.org/W4299286629","https://openalex.org/W6602031475","https://openalex.org/W6639904974","https://openalex.org/W6640015871","https://openalex.org/W6676077707","https://openalex.org/W6676833704","https://openalex.org/W6681190598","https://openalex.org/W6684588631"],"related_works":["https://openalex.org/W2947263763","https://openalex.org/W4288373430","https://openalex.org/W3036260055","https://openalex.org/W4287753704","https://openalex.org/W3158925485","https://openalex.org/W2996735312","https://openalex.org/W3108185025","https://openalex.org/W1850547517","https://openalex.org/W2964125852","https://openalex.org/W3176022311"],"abstract_inverted_index":{"We":[0,76],"propose":[1],"a":[2],"Thompson":[3,23,41],"sampling":[4,24],"based":[5],"learning":[6,120],"algorithm":[7,20],"for":[8],"the":[9,34,37,48,61,64,73,82,86,111,130],"Linear":[10],"Quadratic":[11],"(LQ)":[12],"control":[13],"problem":[14],"with":[15,25],"unknown":[16],"system":[17],"parameters.":[18],"The":[19,43,54],"is":[21,58,68,97,110],"called":[22],"dynamic":[26,38],"episodes":[27,39],"(TSDE)":[28],"where":[29],"two":[30],"stopping":[31,45,56],"criteria":[32],"determine":[33],"lengths":[35],"of":[36,51,63,72,90,119,132],"in":[40,121],"sampling.":[42],"first":[44,112],"criterion":[46,57],"controls":[47],"growth":[49],"rate":[50],"episode":[52],"length.":[53],"second":[55],"triggered":[59],"when":[60],"determinant":[62],"sample":[65],"covariance":[66],"matrix":[67],"less":[69],"than":[70],"half":[71],"previous":[74],"value.":[75],"show":[77],"under":[78],"some":[79],"conditions":[80],"on":[81,116],"prior":[83],"distribution":[84],"that":[85],"expected":[87,117],"(Bayesian)":[88],"regret":[89,118],"TSDE":[91],"accumulated":[92],"up":[93],"to":[94,128],"time":[95],"T":[96],"bounded":[98],"by":[99],"\u00d5(\u221aT).":[100],"Here":[101],"\u00d5":[102,113],"(\u00b7)":[103],"hides":[104],"constants":[105],"and":[106],"logarithmic":[107],"factors.":[108],"This":[109],"(\u221aT)":[114],"bound":[115],"LQ":[122],"control.":[123],"Numerical":[124],"simulations":[125],"are":[126],"provided":[127],"illustrate":[129],"performance":[131],"TSDE.":[133]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}