{"id":"https://openalex.org/W2916603395","doi":"https://doi.org/10.24963/ijcai.2019/386","title":"Perturbed-History Exploration in Stochastic Multi-Armed Bandits","display_name":"Perturbed-History Exploration in Stochastic Multi-Armed Bandits","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2916603395","doi":"https://doi.org/10.24963/ijcai.2019/386","mag":"2916603395"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/386","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/386","pdf_url":"https://www.ijcai.org/proceedings/2019/0386.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0386.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049020775","display_name":"Branislav Kveton","orcid":"https://orcid.org/0000-0002-3965-1367"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Branislav Kveton","raw_affiliation_strings":["Google Research","Google Research,"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Research,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069856068","display_name":"Csaba Szepesv\u00e1ri","orcid":"https://orcid.org/0000-0002-9286-2892"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]},{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["CA","GB"],"is_corresponding":false,"raw_author_name":"Csaba Szepesv\u00e1ri","raw_affiliation_strings":["DeepMind","University of Alberta"],"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013843778","display_name":"Mohammad Ghavamzadeh","orcid":"https://orcid.org/0000-0003-0930-8688"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Mohammad Ghavamzadeh","raw_affiliation_strings":["Facebook AI Research","Facebook AI Research#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research#TAB#","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036934218","display_name":"Craig Boutilier","orcid":"https://orcid.org/0000-0001-9330-4545"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Craig Boutilier","raw_affiliation_strings":["Google Research","Google Research,"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Research,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5049020775"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.25758197,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80451974,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2786","last_page":"2793"},"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":0.9883999824523926,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9746000170707703,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/regret","display_name":"Regret","score":0.9240347146987915},{"id":"https://openalex.org/keywords/bernoullis-principle","display_name":"Bernoulli's principle","score":0.6912873387336731},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5838228464126587},{"id":"https://openalex.org/keywords/argument","display_name":"Argument (complex analysis)","score":0.5539002418518066},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5046161413192749},{"id":"https://openalex.org/keywords/optimism","display_name":"Optimism","score":0.4781300127506256},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4508884847164154},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3124915361404419},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.18855705857276917},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1721070110797882},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.128573477268219},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09504303336143494}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9240347146987915},{"id":"https://openalex.org/C152361515","wikidata":"https://www.wikidata.org/wiki/Q181328","display_name":"Bernoulli's principle","level":2,"score":0.6912873387336731},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5838228464126587},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.5539002418518066},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5046161413192749},{"id":"https://openalex.org/C204017024","wikidata":"https://www.wikidata.org/wiki/Q485446","display_name":"Optimism","level":2,"score":0.4781300127506256},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4508884847164154},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3124915361404419},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18855705857276917},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1721070110797882},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.128573477268219},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09504303336143494},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.24963/ijcai.2019/386","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/386","pdf_url":"https://www.ijcai.org/proceedings/2019/0386.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1902.10089","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.10089","pdf_url":"https://arxiv.org/pdf/1902.10089","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2916603395","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1902.10089","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1902.10089","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1902.10089","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/386","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/386","pdf_url":"https://www.ijcai.org/proceedings/2019/0386.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2916603395.pdf","grobid_xml":"https://content.openalex.org/works/W2916603395.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W50486269","https://openalex.org/W148122774","https://openalex.org/W1501823362","https://openalex.org/W1900560890","https://openalex.org/W2023599408","https://openalex.org/W2039522160","https://openalex.org/W2099213975","https://openalex.org/W2119738618","https://openalex.org/W2123157758","https://openalex.org/W2141645258","https://openalex.org/W2160163723","https://openalex.org/W2166253248","https://openalex.org/W2168405694","https://openalex.org/W2210740898","https://openalex.org/W2555558374","https://openalex.org/W2950064235","https://openalex.org/W2962755588","https://openalex.org/W2962996309","https://openalex.org/W2963007936","https://openalex.org/W2963280733","https://openalex.org/W2963661728","https://openalex.org/W2963695785","https://openalex.org/W2964330179","https://openalex.org/W2964860107","https://openalex.org/W3037875958"],"related_works":["https://openalex.org/W2965432377","https://openalex.org/W2901116712","https://openalex.org/W3124285628","https://openalex.org/W2796393948","https://openalex.org/W2886535806","https://openalex.org/W2603526483","https://openalex.org/W1594658837","https://openalex.org/W2942295458","https://openalex.org/W1553290137","https://openalex.org/W2994057479","https://openalex.org/W2601096073","https://openalex.org/W2576746119","https://openalex.org/W2918266653","https://openalex.org/W2185823609","https://openalex.org/W2953067537","https://openalex.org/W2237158255","https://openalex.org/W3009708787","https://openalex.org/W2914049206","https://openalex.org/W3006831017","https://openalex.org/W2085872558"],"abstract_inverted_index":{"We":[0,64],"propose":[1],"an":[2],"online":[3],"algorithm":[4,15],"for":[5],"cumulative":[6],"regret":[7,74],"minimization":[8],"in":[9,23,36,80],"a":[10,61,84],"stochastic":[11],"multi-armed":[12],"bandit.":[13],"The":[14,47,77],"adds":[16],"O(t)":[17],"i.i.d.":[18],"pseudo-rewards":[19,48],"to":[20,52,94],"its":[21,37],"history":[22],"round":[24],"t":[25],"and":[26,68,101],"then":[27],"pulls":[28],"the":[29,32,72],"arm":[30],"with":[31,60,107],"highest":[33],"average":[34],"reward":[35],"perturbed":[38],"history.":[39],"Therefore,":[40],"we":[41,97],"call":[42],"it":[43,104],"perturbed-history":[44],"exploration":[45],"(PHE).":[46],"are":[49],"carefully":[50],"designed":[51],"offset":[53],"potentially":[54],"underestimated":[55],"mean":[56],"rewards":[57,92],"of":[58,75],"arms":[59],"high":[62],"probability.":[63],"derive":[65],"near-optimal":[66],"gap-dependent":[67],"gap-free":[69],"bounds":[70],"on":[71],"n-round":[73],"PHE.":[76],"key":[78],"step":[79],"our":[81],"analysis":[82],"is":[83,105],"novel":[85],"argument":[86],"that":[87,89,103],"shows":[88],"randomized":[90],"Bernoulli":[91],"lead":[93],"optimism.":[95],"Finally,":[96],"empirically":[98],"evaluate":[99],"PHE":[100],"show":[102],"competitive":[106],"state-of-the-art":[108],"baselines.":[109]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}