{"id":"https://openalex.org/W2740008209","doi":"https://doi.org/10.24963/ijcai.2017/688","title":"On Thompson Sampling and Asymptotic Optimality","display_name":"On Thompson Sampling and Asymptotic Optimality","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2740008209","doi":"https://doi.org/10.24963/ijcai.2017/688","mag":"2740008209"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/688","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/688","pdf_url":"https://www.ijcai.org/proceedings/2017/0688.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2017/0688.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090592321","display_name":"Jan Leike","orcid":null},"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"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jan Leike","raw_affiliation_strings":["DeepMind","FHI, University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"FHI, University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017031238","display_name":"Tor Lattimore","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tor Lattimore","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110938957","display_name":"Laurent Orseau","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Laurent Orseau","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073944062","display_name":"Marcus H\u00fctter","orcid":"https://orcid.org/0000-0002-3263-4097"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Marcus Hutter","raw_affiliation_strings":["Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.7051,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.98982761,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4889","last_page":"4893"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973999857902527,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9948999881744385,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8264894485473633},{"id":"https://openalex.org/keywords/sublinear-function","display_name":"Sublinear function","score":0.7730205059051514},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.7000297904014587},{"id":"https://openalex.org/keywords/countable-set","display_name":"Countable set","score":0.6854830980300903},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.6813821196556091},{"id":"https://openalex.org/keywords/ergodic-theory","display_name":"Ergodic theory","score":0.6528360247612},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5792235136032104},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5379840135574341},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5187582969665527},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.44969233870506287},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4468713700771332},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4299905300140381},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.41625547409057617},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3895127773284912},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.38693469762802124},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.30347776412963867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23651862144470215},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.17551007866859436},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.11014729738235474}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8264894485473633},{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.7730205059051514},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.7000297904014587},{"id":"https://openalex.org/C110729354","wikidata":"https://www.wikidata.org/wiki/Q185478","display_name":"Countable set","level":2,"score":0.6854830980300903},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.6813821196556091},{"id":"https://openalex.org/C122044880","wikidata":"https://www.wikidata.org/wiki/Q5498822","display_name":"Ergodic theory","level":2,"score":0.6528360247612},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5792235136032104},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5379840135574341},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5187582969665527},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.44969233870506287},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4468713700771332},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4299905300140381},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.41625547409057617},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3895127773284912},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.38693469762802124},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.30347776412963867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23651862144470215},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17551007866859436},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.11014729738235474},{"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":2,"locations":[{"id":"doi:10.24963/ijcai.2017/688","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/688","pdf_url":"https://www.ijcai.org/proceedings/2017/0688.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/313140","is_oa":false,"landing_page_url":"http://hdl.handle.net/1885/313140","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17)","raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2017/688","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/688","pdf_url":"https://www.ijcai.org/proceedings/2017/0688.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Life in Land","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740008209.pdf","grobid_xml":"https://content.openalex.org/works/W2740008209.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W844321258","https://openalex.org/W1582436621","https://openalex.org/W1591803298","https://openalex.org/W1850488217","https://openalex.org/W1876044947","https://openalex.org/W1901083042","https://openalex.org/W1911551976","https://openalex.org/W1919575688","https://openalex.org/W1987292194","https://openalex.org/W2039522160","https://openalex.org/W2103708221","https://openalex.org/W2108738385","https://openalex.org/W2111764152","https://openalex.org/W2125710232","https://openalex.org/W2137938746","https://openalex.org/W2142176084","https://openalex.org/W2144863733","https://openalex.org/W2145339207","https://openalex.org/W2146911536","https://openalex.org/W2147871016","https://openalex.org/W2149524486","https://openalex.org/W2158319693","https://openalex.org/W2281341692","https://openalex.org/W2470693974","https://openalex.org/W2523568623","https://openalex.org/W2558819991","https://openalex.org/W2765733960","https://openalex.org/W2782975919","https://openalex.org/W2886070359","https://openalex.org/W2908491431","https://openalex.org/W2949185669","https://openalex.org/W2949186496","https://openalex.org/W2950929549","https://openalex.org/W2952363498","https://openalex.org/W2952787800","https://openalex.org/W2963158178","https://openalex.org/W2963276097","https://openalex.org/W2964108562","https://openalex.org/W3020125231","https://openalex.org/W3037312387","https://openalex.org/W4234228486","https://openalex.org/W4293495159","https://openalex.org/W4294029272","https://openalex.org/W4299502902","https://openalex.org/W4394644466"],"related_works":["https://openalex.org/W2970347269","https://openalex.org/W4287863949","https://openalex.org/W1850488217","https://openalex.org/W3108185025","https://openalex.org/W4287102143","https://openalex.org/W2945119207","https://openalex.org/W3182614517","https://openalex.org/W1850547517","https://openalex.org/W2964125852","https://openalex.org/W3176022311"],"abstract_inverted_index":{"We":[0,28,61],"discuss":[1],"some":[2],"recent":[3],"results":[4],"on":[5],"Thompson":[6,31],"sampling":[7,32],"for":[8],"nonparametric":[9],"reinforcement":[10,69],"learning":[11],"in":[12,37,46,68],"countable":[13],"classes":[14],"of":[15],"general":[16],"stochastic":[17],"environments.":[18],"These":[19],"environments":[20],"can":[21],"be":[22],"non-Markovian,":[23],"non-ergodic,":[24],"and":[25,52],"partially":[26],"observable.":[27],"show":[29],"that":[30,40],"learns":[33],"the":[34,38,49],"environment":[35],"class":[36],"sense":[39],"(1)":[41],"asymptotically":[42],"its":[43],"value":[44,51],"converges":[45],"mean":[47],"to":[48],"optimal":[50],"(2)":[53],"given":[54],"a":[55,64],"recoverability":[56],"assumption":[57],"regret":[58],"is":[59],"sublinear.":[60],"conclude":[62],"with":[63],"discussion":[65],"about":[66],"optimality":[67],"learning.":[70]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":50},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}