{"id":"https://openalex.org/W2904232271","doi":"https://doi.org/10.1609/aaai.v33i01.33016112","title":"Leveraging Observations in Bandits: Between Risks and Benefits","display_name":"Leveraging Observations in Bandits: Between Risks and Benefits","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2904232271","doi":"https://doi.org/10.1609/aaai.v33i01.33016112","mag":"2904232271"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33016112","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33016112","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v33i01.33016112","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007600034","display_name":"Andrei Lupu","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Andrei Lupu","raw_affiliation_strings":["McGill University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069876930","display_name":"Audrey Durand","orcid":"https://orcid.org/0000-0001-9290-8603"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Audrey Durand","raw_affiliation_strings":["McGill University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065836447","display_name":"Doina Precup","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Doina Precup","raw_affiliation_strings":["McGill University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":1.5987,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80555556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"33","issue":"01","first_page":"6112","last_page":"6119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9836000204086304,"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":0.9832000136375427,"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/regret","display_name":"Regret","score":0.935206413269043},{"id":"https://openalex.org/keywords/multi-armed-bandit","display_name":"Multi-armed bandit","score":0.6995976567268372},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6970865726470947},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6799860596656799},{"id":"https://openalex.org/keywords/optimism","display_name":"Optimism","score":0.5544815063476562},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5497145056724548},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.46123170852661133},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.45486822724342346},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4458167552947998},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44089236855506897},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4317011833190918},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.42013463377952576},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.11989712715148926},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1066502034664154}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.935206413269043},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.6995976567268372},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6970865726470947},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6799860596656799},{"id":"https://openalex.org/C204017024","wikidata":"https://www.wikidata.org/wiki/Q485446","display_name":"Optimism","level":2,"score":0.5544815063476562},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5497145056724548},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.46123170852661133},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.45486822724342346},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4458167552947998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44089236855506897},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4317011833190918},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.42013463377952576},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.11989712715148926},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1066502034664154},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33016112","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33016112","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4568","is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4568","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4568/4446","source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33016112","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33016112","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W35251828","https://openalex.org/W157259654","https://openalex.org/W1550621568","https://openalex.org/W1570738427","https://openalex.org/W1977989560","https://openalex.org/W1986014385","https://openalex.org/W2038900621","https://openalex.org/W2069374972","https://openalex.org/W2072655300","https://openalex.org/W2096365673","https://openalex.org/W2112420033","https://openalex.org/W2124637492","https://openalex.org/W2140950724","https://openalex.org/W2166302491","https://openalex.org/W2413102462","https://openalex.org/W2544683879","https://openalex.org/W2698595662","https://openalex.org/W2788807549","https://openalex.org/W2963832131","https://openalex.org/W3121632328","https://openalex.org/W4206567137","https://openalex.org/W6637330856","https://openalex.org/W6644535067","https://openalex.org/W6646884813","https://openalex.org/W6649529041","https://openalex.org/W6678485558","https://openalex.org/W6681018632","https://openalex.org/W6893254818","https://openalex.org/W7034911385","https://openalex.org/W7075680496"],"related_works":["https://openalex.org/W4289341771","https://openalex.org/W3176022311","https://openalex.org/W3114769327","https://openalex.org/W3048056964","https://openalex.org/W2613863488","https://openalex.org/W3046298489","https://openalex.org/W4287690869","https://openalex.org/W2331759129","https://openalex.org/W1850547517","https://openalex.org/W2964125852"],"abstract_inverted_index":{"Imitation":[0],"learning":[1,9,35,188],"has":[2],"been":[3],"widely":[4],"used":[5],"to":[6,16,25,33,119,186],"speed":[7],"up":[8],"in":[10,56,117,150,189],"novice":[11],"agents,":[12],"by":[13,28,138],"allowing":[14],"them":[15],"leverage":[17],"existing":[18],"data":[19],"from":[20],"experts.":[21],"Allowing":[22],"an":[23,66],"agent":[24,42,67],"be":[26],"influenced":[27],"external":[29],"observations":[30],"can":[31,77],"benefit":[32],"the":[34,41,57,85,92,96,112,115,121,126,132,151,161,164,168,190,207],"process,":[36],"but":[37,76],"it":[38,141],"also":[39,78],"puts":[40],"at":[43],"risk":[44],"of":[45,59,114,128,146,153,163],"following":[46],"sub-optimal":[47],"behaviours.":[48],"In":[49],"this":[50,54,129],"paper,":[51],"we":[52,63,159],"study":[53],"problem":[55],"context":[58],"bandits.":[60],"More":[61],"specifically,":[62],"consider":[64],"that":[65,106,140],"(learner)":[68],"is":[69],"interacting":[70,83],"with":[71,84,202],"a":[72,80,101,143,154],"bandit-style":[73],"decision":[74],"task,":[75],"observe":[79],"target":[81,116,170],"policy":[82],"same":[86],"environment.":[87],"The":[88],"learner":[89],"observes":[90],"only":[91],"target\u2019s":[93],"actions,":[94],"not":[95],"rewards":[97],"obtained.":[98],"We":[99,124,172],"introduce":[100],"new":[102],"bandit":[103,192],"optimism":[104,109],"modifier":[105],"uses":[107],"conditional":[108],"contingent":[110],"on":[111,131,167],"actions":[113],"order":[118,147],"guide":[120],"agent\u2019s":[122],"exploration.":[123],"analyze":[125],"effect":[127],"modification":[130],"well-known":[133],"Upper":[134],"Confidence":[135],"Bound":[136],"algorithm":[137],"proving":[139],"preserves":[142],"regret":[144,166],"upper-bound":[145],"O(lnT),":[148],"even":[149],"presence":[152],"very":[155],"poor":[156],"target,":[157],"and":[158,211],"derive":[160],"dependency":[162],"expected":[165],"general":[169],"policy.":[171],"provide":[173],"empirical":[174],"results":[175],"showing":[176],"both":[177],"great":[178],"benefits":[179],"as":[180,182],"well":[181],"certain":[183],"limitations":[184],"inherent":[185],"observational":[187],"multi-armed":[191],"setting.":[193],"Experiments":[194],"are":[195],"conducted":[196],"using":[197],"targets":[198],"satisfying":[199],"theoretical":[200],"assumptions":[201],"high":[203],"probability,":[204],"thus":[205],"narrowing":[206],"gap":[208],"between":[209],"theory":[210],"application.":[212]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}