{"id":"https://openalex.org/W2029955117","doi":"https://doi.org/10.1109/adprl.2014.7010620","title":"Pareto Upper Confidence Bounds algorithms: An empirical study","display_name":"Pareto Upper Confidence Bounds algorithms: An empirical study","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2029955117","doi":"https://doi.org/10.1109/adprl.2014.7010620","mag":"2029955117"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2014.7010620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016131956","display_name":"M\u0103d\u0103lina M. Drugan","orcid":"https://orcid.org/0000-0001-9497-3134"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Madalina M Drugan","raw_affiliation_strings":["Artificial Intelligence Lab, Vrije Universiteit, Brussel, Belgium","Artificial Intelligence Lab, Vrije Universiteit Brussel, Belgium"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Lab, Vrije Universiteit, Brussel, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Artificial Intelligence Lab, Vrije Universiteit Brussel, Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064553018","display_name":"Ann Now\u00e9","orcid":"https://orcid.org/0000-0001-6346-4564"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Ann Nowe","raw_affiliation_strings":["Artificial Intelligence Lab, Vrije Universiteit, Brussel, Belgium","Artificial Intelligence Lab, Vrije Universiteit Brussel, Belgium"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Lab, Vrije Universiteit, Brussel, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Artificial Intelligence Lab, Vrije Universiteit Brussel, Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030973642","display_name":"Bernard Manderick","orcid":"https://orcid.org/0000-0002-9020-0510"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Bernard Manderick","raw_affiliation_strings":["Artificial Intelligence Lab, Vrije Universiteit, Brussel, Belgium","Artificial Intelligence Lab, Vrije Universiteit Brussel, Belgium"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Lab, Vrije Universiteit, Brussel, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Artificial Intelligence Lab, Vrije Universiteit Brussel, Belgium","institution_ids":["https://openalex.org/I13469542"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016131956"],"corresponding_institution_ids":["https://openalex.org/I13469542"],"apc_list":null,"apc_paid":null,"fwci":0.8408,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78112296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"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":0.9998999834060669,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.6706771850585938},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.6527104377746582},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.6212036609649658},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5944190621376038},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5824775695800781},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5592496395111084},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.5534720420837402},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4672289788722992},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4650821089744568},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.45232731103897095},{"id":"https://openalex.org/keywords/pareto-optimal","display_name":"Pareto optimal","score":0.4311865270137787},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27781152725219727},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20206528902053833},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1050085723400116}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.6706771850585938},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.6527104377746582},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.6212036609649658},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5944190621376038},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5824775695800781},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5592496395111084},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.5534720420837402},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4672289788722992},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4650821089744568},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.45232731103897095},{"id":"https://openalex.org/C2986314615","wikidata":"https://www.wikidata.org/wiki/Q36829","display_name":"Pareto optimal","level":3,"score":0.4311865270137787},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27781152725219727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20206528902053833},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1050085723400116},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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":8,"locations":[{"id":"doi:10.1109/adprl.2014.7010620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/f47e5580-ec58-4e6c-b6fe-6d09643cd647","is_oa":false,"landing_page_url":"https://research.tue.nl/en/publications/f47e5580-ec58-4e6c-b6fe-6d09643cd647","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Drugan, M M, Now\u00e9, A & Manderick, B 2014, Pareto upper confidence bounds algorithms : an empirical study. in 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), 9-12 December 2014, Orlando, Florida., 7010620, Institute of Electrical and Electronics Engineers, Piscataway, pp. 1-8, 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL 2014), Orlando, Florida, United States, 9/12/14. https://doi.org/10.1109/ADPRL.2014.7010620","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:839860","is_oa":false,"landing_page_url":"http://library.tue.nl/csp/dare/LinkToRepository.csp?recordnumber=839860","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:library.tue.nl:839860","is_oa":false,"landing_page_url":"http://repository.tue.nl/839860","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:library.tue.nl:889208","is_oa":false,"landing_page_url":"http://repository.tue.nl/889208","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.tue.nl:publications/f47e5580-ec58-4e6c-b6fe-6d09643cd647","is_oa":false,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=84946686477&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Drugan, M M, Now\u00e9, A & Manderick, B 2014, Pareto upper confidence bounds algorithms : an empirical study. in 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), 9-12 December 2014, Orlando, Florida., 7010620, Institute of Electrical and Electronics Engineers, Piscataway, pp. 1-8, 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL 2014), Orlando, Florida, United States, 9/12/14. https://doi.org/10.1109/ADPRL.2014.7010620","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:90720","is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/pareto-upper-confidence-bounds-algorithms-an-empirical-study(01a8e841-3618-4a26-b8dc-981337f3c04b).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"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":"article"},{"id":"pmh:tue:oai:pure.tue.nl:publications/f47e5580-ec58-4e6c-b6fe-6d09643cd647","is_oa":false,"landing_page_url":"https://research.tue.nl/nl/publications/f47e5580-ec58-4e6c-b6fe-6d09643cd647","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), 9-12 December 2014, Orlando, Florida, 1 - 8","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W288089086","https://openalex.org/W1553290137","https://openalex.org/W1975779216","https://openalex.org/W2012612381","https://openalex.org/W2040376780","https://openalex.org/W2049934117","https://openalex.org/W2063375245","https://openalex.org/W2091929427","https://openalex.org/W2094187318","https://openalex.org/W2095602422","https://openalex.org/W2098907614","https://openalex.org/W2102660061","https://openalex.org/W2103405567","https://openalex.org/W2152213878","https://openalex.org/W2165962877","https://openalex.org/W2168405694","https://openalex.org/W2182124586","https://openalex.org/W2950929549","https://openalex.org/W2963812065","https://openalex.org/W3100895096","https://openalex.org/W3103262232","https://openalex.org/W3132923784","https://openalex.org/W4297785562","https://openalex.org/W6632992360","https://openalex.org/W6675394771","https://openalex.org/W6681605418","https://openalex.org/W6684585682","https://openalex.org/W6685793570"],"related_works":["https://openalex.org/W1963790170","https://openalex.org/W2073298047","https://openalex.org/W2033790662","https://openalex.org/W2090178682","https://openalex.org/W2586328217","https://openalex.org/W2049264236","https://openalex.org/W2001591765","https://openalex.org/W4241467429","https://openalex.org/W2073147994","https://openalex.org/W1588199609"],"abstract_inverted_index":{"Many":[0],"real-world":[1],"stochastic":[2],"environments":[3,7],"are":[4,16,33],"inherently":[5],"multi-objective":[6,12,30,160,177],"with":[8,39,118],"conflicting":[9],"objectives.":[10],"The":[11,76],"multi-armed":[13,24,161],"bandits":[14,25],"(MOMAB)":[15],"extensions":[17],"of":[18,78,91,102,110,140,158],"the":[19,51,62,73,79,89,95,108,111,119,124,138,151,156,169,175],"classical,":[20],"i.e.":[21,84,137],"single":[22,63],"objective,":[23],"to":[26,36,68,87,154],"reward":[27,69],"vectors":[28,70],"and":[29,123],"optimisation":[31],"techniques":[32],"often":[34],"required":[35],"design":[37],"mechanisms":[38],"an":[40,133],"efficient":[41],"exploration":[42],"/":[43],"exploitation":[44],"trade-off.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49],"propose":[50,144],"improved":[52,65,80],"Pareto":[53,81,96,113,120],"Upper":[54],"Confidence":[55],"Bound":[56],"(iPUCB)":[57],"algorithm":[58,67,117,122],"that":[59,166],"straightforwardly":[60],"extends":[61],"objective":[64],"UCB":[66,82],"by":[71],"deleting":[72],"suboptimal":[74],"arms.":[75],"goal":[77],"algorithm,":[83],"iPUCB,":[85],"is":[86],"identify":[88],"set":[90],"best":[92],"arms,":[93],"or":[94],"front,":[97],"in":[98],"a":[99,128,145,159],"fixed":[100],"budget":[101],"arm":[103],"pulls.":[104],"We":[105,143,164],"experimentally":[106],"compare":[107],"performance":[109,157],"proposed":[112],"upper":[114],"confidence":[115],"bound":[116],"UCB1":[121],"Hoeffding":[125],"race":[126],"on":[127,150,174],"bi-objective":[129],"example":[130],"coming":[131],"from":[132],"industrial":[134],"control":[135],"applications,":[136],"engagement":[139],"wet":[141],"clutches.":[142],"new":[146],"regret":[147],"metric":[148],"based":[149],"Kullback-Leibler":[152],"divergence":[153],"measure":[155],"bandit":[162],"algorithm.":[163],"show":[165],"iPUCB":[167],"outperforms":[168],"other":[170],"two":[171],"tested":[172],"algorithms":[173],"given":[176],"environment.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}