{"id":"https://openalex.org/W2992545808","doi":"https://doi.org/10.1109/allerton.2019.8919864","title":"Learning to Control in Metric Space with Optimal Regret","display_name":"Learning to Control in Metric Space with Optimal Regret","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2992545808","doi":"https://doi.org/10.1109/allerton.2019.8919864","mag":"2992545808"},"language":"en","primary_location":{"id":"doi:10.1109/allerton.2019.8919864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2019.8919864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5079423586","display_name":"Chengzhuo Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengzhuo Ni","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072096775","display_name":"Lin F. Yang","orcid":"https://orcid.org/0000-0003-4602-3366"},"institutions":[{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin F. Yang","raw_affiliation_strings":["UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA","institution_ids":["https://openalex.org/I2799798094"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100707460","display_name":"Mengdi Wang","orcid":"https://orcid.org/0000-0002-2101-9507"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mengdi Wang","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6608,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.94139013,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"726","last_page":"733"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9993000030517578,"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":0.9993000030517578,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"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/T11178","display_name":"Receptor Mechanisms and Signaling","score":0.9854999780654907,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.8486306071281433},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6693227887153625},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5670539140701294},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.531414806842804},{"id":"https://openalex.org/keywords/metric-space","display_name":"Metric space","score":0.5259535312652588},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.497224360704422},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.49669915437698364},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.4856628179550171},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4664442241191864},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4557684063911438},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.45001593232154846},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.42964670062065125},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42638295888900757},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37901246547698975},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.3349883556365967},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.27323755621910095},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.2654622197151184},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.1653130054473877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15619197487831116},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09328559041023254}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8486306071281433},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6693227887153625},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5670539140701294},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.531414806842804},{"id":"https://openalex.org/C198043062","wikidata":"https://www.wikidata.org/wiki/Q180953","display_name":"Metric space","level":2,"score":0.5259535312652588},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.497224360704422},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.49669915437698364},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.4856628179550171},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4664442241191864},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4557684063911438},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.45001593232154846},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.42964670062065125},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42638295888900757},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37901246547698975},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3349883556365967},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.27323755621910095},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2654622197151184},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.1653130054473877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15619197487831116},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09328559041023254},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/allerton.2019.8919864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2019.8919864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W21891419","https://openalex.org/W41554520","https://openalex.org/W1504915502","https://openalex.org/W1509780496","https://openalex.org/W1546944959","https://openalex.org/W1591992921","https://openalex.org/W1757796397","https://openalex.org/W1915973093","https://openalex.org/W1969276875","https://openalex.org/W2023146810","https://openalex.org/W2098432798","https://openalex.org/W2099179721","https://openalex.org/W2121863487","https://openalex.org/W2123979492","https://openalex.org/W2125510930","https://openalex.org/W2518564545","https://openalex.org/W2544192463","https://openalex.org/W2568646110","https://openalex.org/W2769648743","https://openalex.org/W2805379554","https://openalex.org/W2805861379","https://openalex.org/W2950872739","https://openalex.org/W2951333509","https://openalex.org/W2956123884","https://openalex.org/W2963434013","https://openalex.org/W2963681938","https://openalex.org/W2964054583","https://openalex.org/W2964284806","https://openalex.org/W2964299116","https://openalex.org/W3020125231","https://openalex.org/W4294183581","https://openalex.org/W4298857966","https://openalex.org/W6632870548","https://openalex.org/W6635516443","https://openalex.org/W6637967152","https://openalex.org/W6638898712","https://openalex.org/W6639039794","https://openalex.org/W6639926649","https://openalex.org/W6674913155","https://openalex.org/W6678900246","https://openalex.org/W6679954139","https://openalex.org/W6726187413","https://openalex.org/W6728843186","https://openalex.org/W6736209634","https://openalex.org/W6746523204","https://openalex.org/W6751694215","https://openalex.org/W6751959615","https://openalex.org/W6752368512","https://openalex.org/W6763257922"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2101991911","https://openalex.org/W2155070487","https://openalex.org/W4311589891","https://openalex.org/W2807018115","https://openalex.org/W2051622126"],"abstract_inverted_index":{"We":[0,45,67,110],"study":[1],"online":[2],"reinforcement":[3,51],"learning":[4,52],"for":[5,126],"finite-horizon":[6],"deterministic":[7],"control":[8],"systems":[9],"with":[10,33,104],"arbitrary":[11],"state":[12,27],"and":[13,20,28,43,94,135],"action":[14,29],"spaces.":[15],"Suppose":[16],"the":[17,26,38,70,73,83,86,97,101,107,132,136,147,151],"transition":[18,129],"dynamics":[19],"reward":[21],"function":[22,57],"is":[23,31,78,82,90,96],"unknown,":[24],"but":[25],"space":[30,103],"endowed":[32],"a":[34,47,56,91,113],"metric":[35],"that":[36,54,69],"characterizes":[37],"proximity":[39],"between":[40],"different":[41],"states":[42],"actions.":[44],"provide":[46],"surprisingly":[48],"simple":[49],"upper-confidence":[50],"algorithm":[53,74],"uses":[55],"approximation":[58],"oracle":[59],"to":[60,106,124],"estimate":[61],"optimistic":[62],"Q":[63],"functions":[64,140],"from":[65],"experiences.":[66],"show":[68],"regret":[71,115],"of":[72,85,100,144],"after":[75],"K":[76],"episodes":[77],"$o(DLK)^{\\frac{d}{d+1}}H$":[79],"where":[80,138,146],"D":[81],"diameter":[84],"state-action":[87,102],"space,":[88],"L":[89],"smoothness":[92],"parameter,":[93],"d":[95],"doubling":[98],"dimension":[99],"respect":[105],"given":[108],"metric.":[109],"also":[111,149],"establish":[112],"near-matching":[114],"lower":[116],"bound.":[117],"The":[118],"proposed":[119],"method":[120,148],"can":[121],"be":[122],"adapted":[123],"work":[125],"more":[127],"structured":[128],"systems,":[130],"including":[131],"finite-state":[133],"case":[134,137],"value":[139],"are":[141],"linear":[142],"combinations":[143],"features,":[145],"achieve":[150],"optimal":[152],"regret.":[153]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}