{"id":"https://openalex.org/W3041982052","doi":"https://doi.org/10.1162/neco_a_01539","title":"Recurrent Neural-Linear Posterior Sampling for Nonstationary Contextual Bandits","display_name":"Recurrent Neural-Linear Posterior Sampling for Nonstationary Contextual Bandits","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W3041982052","doi":"https://doi.org/10.1162/neco_a_01539","mag":"3041982052","pmid":"https://pubmed.ncbi.nlm.nih.gov/36112923"},"language":"en","primary_location":{"id":"doi:10.1162/neco_a_01539","is_oa":true,"landing_page_url":"https://doi.org/10.1162/neco_a_01539","pdf_url":"https://direct.mit.edu/neco/article-pdf/34/11/2232/2048426/neco_a_01539.pdf","source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://direct.mit.edu/neco/article-pdf/34/11/2232/2048426/neco_a_01539.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101696375","display_name":"Aditya Ramesh","orcid":"https://orcid.org/0000-0001-5984-8282"},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]},{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Aditya Ramesh","raw_affiliation_strings":["Istituto Dalle Molle di Studi sull'Intelligenza Artificiale, Lugano 6962, Switzerland","Scuola universitaria professionale della Svizzera italiana, Lugano 6962, Switzerland aditya.ramesh@idsia.ch","Universit\u00e0 della Svizzera italiana, Lugano 6962, Switzerland","Scuola universitaria professionale della Svizzera italiana, Lugano 6962, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto Dalle Molle di Studi sull'Intelligenza Artificiale, Lugano 6962, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Scuola universitaria professionale della Svizzera italiana, Lugano 6962, Switzerland aditya.ramesh@idsia.ch","institution_ids":["https://openalex.org/I57201433"]},{"raw_affiliation_string":"Universit\u00e0 della Svizzera italiana, Lugano 6962, Switzerland","institution_ids":["https://openalex.org/I57201433"]},{"raw_affiliation_string":"Scuola universitaria professionale della Svizzera italiana, Lugano 6962, Switzerland","institution_ids":["https://openalex.org/I57201433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031951061","display_name":"Paulo Rauber","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Paulo Rauber","raw_affiliation_strings":["Queen Mary University of London, London E1 4 NS, U.K. p.rauber@qmul.ac.uk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London, London E1 4 NS, U.K. p.rauber@qmul.ac.uk","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060576718","display_name":"Michelangelo Conserva","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Michelangelo Conserva","raw_affiliation_strings":["Queen Mary University of London, London E1 4 NS, U.K. m.conserva@qmul.ac.uk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London, London E1 4 NS, U.K. m.conserva@qmul.ac.uk","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071172037","display_name":"J\u00fcrgen Schmidhuber","orcid":null},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]},{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]},{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["CH","SA"],"is_corresponding":true,"raw_author_name":"J\u00fcrgen Schmidhuber","raw_affiliation_strings":["Istituto Dalle Molle di Studi sull'Intelligenza Artificiale, Lugano 6962, Switzerland","King Abdullah University of Science and Technology, Thuwal, Saudi Arabia juergen@idsia.ch","NNAISENSE, Lugano 6900, Switzerland","Scuola universitaria professionale della Svizzera italiana, Lugano 6962, Switzerland","Universit\u00e0 della Svizzera italiana, Lugano 6962, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto Dalle Molle di Studi sull'Intelligenza Artificiale, Lugano 6962, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"King Abdullah University of Science and Technology, Thuwal, Saudi Arabia juergen@idsia.ch","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"NNAISENSE, Lugano 6900, Switzerland","institution_ids":[]},{"raw_affiliation_string":"Scuola universitaria professionale della Svizzera italiana, Lugano 6962, Switzerland","institution_ids":["https://openalex.org/I57201433"]},{"raw_affiliation_string":"Universit\u00e0 della Svizzera italiana, Lugano 6962, Switzerland","institution_ids":["https://openalex.org/I57201433"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031951061","https://openalex.org/A5060576718","https://openalex.org/A5071172037","https://openalex.org/A5101696375"],"corresponding_institution_ids":["https://openalex.org/I166337079","https://openalex.org/I2614128279","https://openalex.org/I57201433","https://openalex.org/I71920554"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00397449,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":"11","first_page":"2232","last_page":"2272"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9897000193595886,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9889000058174133,"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/sampling","display_name":"Sampling (signal processing)","score":0.5367359519004822},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.5212105512619019},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.473969429731369},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45492875576019287},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4402036964893341},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.430192232131958},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4104382395744324},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.377195805311203},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34025588631629944},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.3118211030960083},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1104796826839447}],"concepts":[{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5367359519004822},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.5212105512619019},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.473969429731369},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45492875576019287},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4402036964893341},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.430192232131958},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4104382395744324},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.377195805311203},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34025588631629944},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3118211030960083},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1104796826839447},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1162/neco_a_01539","is_oa":true,"landing_page_url":"https://doi.org/10.1162/neco_a_01539","pdf_url":"https://direct.mit.edu/neco/article-pdf/34/11/2232/2048426/neco_a_01539.pdf","source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},{"id":"pmid:36112923","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36112923","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural computation","raw_type":null},{"id":"pmh:oai:arXiv.org:2007.04750","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.04750","pdf_url":"https://arxiv.org/pdf/2007.04750","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":null,"raw_type":"text"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/80696","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/80696","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:repository.kaust.edu.sa:10754/681559","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/681559","pdf_url":null,"source":{"id":"https://openalex.org/S4306401596","display_name":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71920554","host_organization_name":"King Abdullah University of Science and Technology","host_organization_lineage":["https://openalex.org/I71920554"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1162/neco_a_01539","is_oa":true,"landing_page_url":"https://doi.org/10.1162/neco_a_01539","pdf_url":"https://direct.mit.edu/neco/article-pdf/34/11/2232/2048426/neco_a_01539.pdf","source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3041982052.pdf","grobid_xml":"https://content.openalex.org/works/W3041982052.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W157259654","https://openalex.org/W1491541693","https://openalex.org/W1506806321","https://openalex.org/W1570963478","https://openalex.org/W1663973292","https://openalex.org/W2039522160","https://openalex.org/W2064675550","https://openalex.org/W2108114251","https://openalex.org/W2119738618","https://openalex.org/W2136848157","https://openalex.org/W2166253248","https://openalex.org/W2539298695","https://openalex.org/W2550182557","https://openalex.org/W2578206533","https://openalex.org/W2604272474","https://openalex.org/W2773557179","https://openalex.org/W2911079225","https://openalex.org/W2942494530","https://openalex.org/W2949231465","https://openalex.org/W2962739885","https://openalex.org/W2964121744","https://openalex.org/W2964132277","https://openalex.org/W2964133879","https://openalex.org/W2964330179","https://openalex.org/W2970728282","https://openalex.org/W3012582392","https://openalex.org/W3094031981","https://openalex.org/W3120740533","https://openalex.org/W4299286629","https://openalex.org/W4300971732","https://openalex.org/W6631190155","https://openalex.org/W6676576766","https://openalex.org/W6684588631","https://openalex.org/W6728788707","https://openalex.org/W6747890380","https://openalex.org/W6755675075","https://openalex.org/W6758070570","https://openalex.org/W6767928194","https://openalex.org/W6779482193","https://openalex.org/W6784171646"],"related_works":["https://openalex.org/W2166253248","https://openalex.org/W4286896030","https://openalex.org/W2032094637","https://openalex.org/W2040227828","https://openalex.org/W2060045818","https://openalex.org/W2131935101","https://openalex.org/W856257623","https://openalex.org/W2892315154","https://openalex.org/W2622395160","https://openalex.org/W2607502872"],"abstract_inverted_index":{"An":[0],"agent":[1,97],"in":[2,21],"a":[3,36,40,50,61,85,105,115,127,178,193],"nonstationary":[4,37,134,158],"contextual":[5,116,131],"bandit":[6,118,159],"problem":[7,38,42],"should":[8],"balance":[9],"between":[10,95],"exploration":[11],"and":[12,98,132],"the":[13,81,90,96,99],"exploitation":[14],"of":[15,64,93,107,130],"(periodic":[16],"or":[17,59],"structured)":[18],"patterns":[19],"present":[20],"its":[22,143],"previous":[23],"experiences.":[24],"Handcrafting":[25],"an":[26,31,75],"appropriate":[27],"historical":[28,53,149],"context":[29,54,83],"is":[30,163],"attractive":[32],"alternative":[33],"to":[34,69,79,166],"transform":[35],"into":[39],"stationary":[41],"that":[43,77,137,189],"can":[44],"be":[45],"solved":[46],"efficiently.":[47],"However,":[48],"even":[49],"carefully":[51],"designed":[52],"may":[55,190],"introduce":[56],"spurious":[57],"relationships":[58],"lack":[60],"convenient":[62],"representation":[63],"crucial":[65],"information.":[66],"In":[67],"order":[68],"address":[70],"these":[71],"issues,":[72],"we":[73,175],"propose":[74],"approach":[76,102,140],"learns":[78],"represent":[80],"relevant":[82],"for":[84,171,182,195],"decision":[86],"based":[87,120],"solely":[88],"on":[89,104,121,126],"raw":[91],"history":[92],"interactions":[94],"environment.":[100],"This":[101],"relies":[103],"combination":[106],"features":[108],"extracted":[109],"by":[110],"recurrent":[111,139],"neural":[112],"networks":[113],"with":[114,186],"linear":[117,183],"algorithm":[119],"posterior":[122,184],"sampling.":[123],"Our":[124],"experiments":[125],"diverse":[128],"selection":[129],"noncontextual":[133],"problems":[135],"show":[136],"our":[138,172],"consistently":[141],"outperforms":[142],"feedforward":[144],"counterpart,":[145],"which":[146],"requires":[147],"handcrafted":[148],"contexts,":[150],"while":[151],"being":[152],"more":[153],"widely":[154],"applicable":[155],"than":[156],"conventional":[157],"algorithms.":[160],"Although":[161],"it":[162],"very":[164],"difficult":[165],"provide":[167],"theoretical":[168,197],"performance":[169],"guarantees":[170],"new":[173],"approach,":[174],"also":[176],"prove":[177],"novel":[179],"regret":[180],"bound":[181],"sampling":[185],"measurement":[187],"error":[188],"serve":[191],"as":[192],"foundation":[194],"future":[196],"work.":[198]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}