{"id":"https://openalex.org/W2965276722","doi":"https://doi.org/10.24963/ijcai.2019/459","title":"Unifying the Stochastic and the Adversarial Bandits with Knapsack","display_name":"Unifying the Stochastic and the Adversarial Bandits with Knapsack","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2965276722","doi":"https://doi.org/10.24963/ijcai.2019/459","mag":"2965276722"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/459","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/459","pdf_url":"https://www.ijcai.org/proceedings/2019/0459.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0459.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063692433","display_name":"Anshuka Rangi","orcid":"https://orcid.org/0000-0002-8462-7892"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anshuka Rangi","raw_affiliation_strings":["University of California, San Diego,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego,","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075999338","display_name":"Massimo Franceschetti","orcid":"https://orcid.org/0000-0002-4057-8152"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Massimo Franceschetti","raw_affiliation_strings":["University of California, San Diego,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego,","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":null,"display_name":"Long Tran-Thanh","orcid":null},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Long Tran-Thanh","raw_affiliation_strings":["University of Southampton"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southampton","institution_ids":["https://openalex.org/I43439940"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3311","last_page":"3317"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.998199999332428,"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":0.9973000288009644,"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":0.8896117806434631},{"id":"https://openalex.org/keywords/knapsack-problem","display_name":"Knapsack problem","score":0.6620545387268066},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6284503936767578},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5426798462867737},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5223737359046936},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5149295926094055},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.48512300848960876},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.42868342995643616},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.42517468333244324},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3474084734916687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2914091944694519},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1480007767677307},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.11437267065048218}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8896117806434631},{"id":"https://openalex.org/C113138325","wikidata":"https://www.wikidata.org/wiki/Q864457","display_name":"Knapsack problem","level":2,"score":0.6620545387268066},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6284503936767578},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5426798462867737},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5223737359046936},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5149295926094055},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.48512300848960876},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.42868342995643616},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.42517468333244324},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3474084734916687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2914091944694519},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1480007767677307},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.11437267065048218},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/459","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/459","pdf_url":"https://www.ijcai.org/proceedings/2019/0459.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"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/459","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/459","pdf_url":"https://www.ijcai.org/proceedings/2019/0459.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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965276722.pdf","grobid_xml":"https://content.openalex.org/works/W2965276722.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W138005451","https://openalex.org/W165458731","https://openalex.org/W1794753160","https://openalex.org/W2029241234","https://openalex.org/W2077902449","https://openalex.org/W2400128071","https://openalex.org/W2402892507","https://openalex.org/W2474012247","https://openalex.org/W2573607665","https://openalex.org/W2769948160","https://openalex.org/W2788830868","https://openalex.org/W2794925984","https://openalex.org/W2808216250","https://openalex.org/W2886942242","https://openalex.org/W2914597131","https://openalex.org/W2950303912","https://openalex.org/W2951814533","https://openalex.org/W2965276722","https://openalex.org/W2971977212","https://openalex.org/W3115063569","https://openalex.org/W4289367500","https://openalex.org/W4295847265","https://openalex.org/W4298023569"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W241127407","https://openalex.org/W4376155396","https://openalex.org/W2381035939","https://openalex.org/W2468477307","https://openalex.org/W2910645127","https://openalex.org/W162895179","https://openalex.org/W1521824362","https://openalex.org/W1947085858","https://openalex.org/W2168163332"],"abstract_inverted_index":{"This":[0,65],"work":[1],"investigates":[2],"the":[3,21,25,33,40,49,52,55,76,79,87,92,100,112,116,122,135,147,152,155,188,191,194,201,207,210,219,233,248],"adversarial":[4,136,208],"Bandits":[5],"with":[6,32,218],"Knapsack":[7],"(BwK)":[8],"learning":[9,101,173,224],"problem,":[10],"where":[11,151,190],"a":[12,29,105,169,240,244],"player":[13,36],"repeatedly":[14],"chooses":[15],"to":[16,47,168,200,232],"perform":[17,48],"an":[18,63,141],"action,":[19,26],"pays":[20],"corresponding":[22,86],"cost":[23,85,98,221],"of":[24,57,71,99,115,193,235],"and":[27,51,54,91,109,139,154,180,198,226],"receives":[28],"reward":[30],"associated":[31],"action.":[34],"The":[35],"is":[37,67,118,131,243],"constrained":[38],"by":[39,62,175,239],"maximum":[41,220],"budget":[42],"that":[43,111,205],"can":[44],"be":[45],"spent":[46],"actions,":[50],"rewards":[53,82,95,153],"costs":[56,156,192,237],"these":[58],"actions":[59,195],"are":[60,157,165,196,227],"assigned":[61],"adversary.":[64],"setting":[66,150],"studied":[68],"in":[69,121,134,146,230,247],"terms":[70],"expected":[72,81,94,113,144],"regret,":[73],"defined":[74],"as":[75],"difference":[77],"between":[78],"total":[80,93],"per":[83,96],"unit":[84,97],"best":[88],"fixed":[89],"action":[90],"algorithm.":[102],"We":[103,124,203],"propose":[104,126],"novel":[106],"algorithm":[107,117,128,178],"EXP3.BwK":[108],"show":[110,204],"regret":[114,145,212],"order":[119,132],"optimal":[120,133,143],"budget.":[123,202],"then":[125,166],"another":[127,177],"EXP3++.BwK,":[129],"which":[130,242],"BwK":[137,149,249],"setting,":[138,174,209],"incurs":[140],"almost":[142],"stochastic":[148],"drawn":[158],"from":[159],"unknown":[160],"underlying":[161],"distributions.":[162],"These":[163],"results":[164],"extended":[167],"more":[170],"general":[171],"online":[172],"designing":[176],"EXP3++.LwK":[179],"providing":[181],"its":[182],"performance":[183],"guarantees.":[184],"Finally,":[185],"we":[186],"investigate":[187],"scenario":[189],"large":[197],"comparable":[199],"for":[206,222],"achievable":[211],"bounds":[213],"scale":[214],"at":[215],"least":[216],"linearly":[217],"any":[223],"algorithm,":[225],"significantly":[228],"worse":[229],"comparison":[231],"case":[234],"having":[236],"bounded":[238],"constant,":[241],"common":[245],"assumption":[246],"literature.":[250]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}