{"id":"https://openalex.org/W2039670868","doi":"https://doi.org/10.1109/adprl.2014.7010619","title":"Annealing-pareto multi-objective multi-armed bandit algorithm","display_name":"Annealing-pareto multi-objective multi-armed bandit algorithm","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2039670868","doi":"https://doi.org/10.1109/adprl.2014.7010619","mag":"2039670868"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2014.7010619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010619","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/A5068375489","display_name":"Saba Q. Yahyaa","orcid":null},"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":"Saba Q. Yahyaa","raw_affiliation_strings":["Department of Computer Science, Vrije Universiteit Brussel, Brussels, Belgium","Vrije Universiteit Brussel, Department of Computer Science, Pleinlaan 2, 1050 Brussels, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Vrije Universiteit Brussel, Department of Computer Science, Pleinlaan 2, 1050 Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","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":false,"raw_author_name":"Madalina M. Drugan","raw_affiliation_strings":["Department of Computer Science, Vrije Universiteit Brussel, Brussels, Belgium","Vrije Universiteit Brussel, Department of Computer Science, Pleinlaan 2, 1050 Brussels, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Vrije Universiteit Brussel, Department of Computer Science, Pleinlaan 2, 1050 Brussels, 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":["Department of Computer Science, Vrije Universiteit Brussel, Brussels, Belgium","Vrije Universiteit Brussel, Department of Computer Science, Pleinlaan 2, 1050 Brussels, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Vrije Universiteit Brussel, Department of Computer Science, Pleinlaan 2, 1050 Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068375489"],"corresponding_institution_ids":["https://openalex.org/I13469542"],"apc_list":null,"apc_paid":null,"fwci":2.9426,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.91010118,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"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":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":0.9987000226974487,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.8554891347885132},{"id":"https://openalex.org/keywords/pareto-interpolation","display_name":"Pareto interpolation","score":0.7708882093429565},{"id":"https://openalex.org/keywords/simulated-annealing","display_name":"Simulated annealing","score":0.7353004217147827},{"id":"https://openalex.org/keywords/pareto-analysis","display_name":"Pareto analysis","score":0.6654961109161377},{"id":"https://openalex.org/keywords/lomax-distribution","display_name":"Lomax distribution","score":0.652662456035614},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6103394031524658},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.5820394158363342},{"id":"https://openalex.org/keywords/pareto-distribution","display_name":"Pareto distribution","score":0.48643064498901367},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4291606843471527},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3858509361743927},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15793585777282715},{"id":"https://openalex.org/keywords/generalized-pareto-distribution","display_name":"Generalized Pareto distribution","score":0.1399242877960205}],"concepts":[{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.8554891347885132},{"id":"https://openalex.org/C38814450","wikidata":"https://www.wikidata.org/wiki/Q7136870","display_name":"Pareto interpolation","level":4,"score":0.7708882093429565},{"id":"https://openalex.org/C126980161","wikidata":"https://www.wikidata.org/wiki/Q863783","display_name":"Simulated annealing","level":2,"score":0.7353004217147827},{"id":"https://openalex.org/C118127601","wikidata":"https://www.wikidata.org/wiki/Q3797610","display_name":"Pareto analysis","level":3,"score":0.6654961109161377},{"id":"https://openalex.org/C18249693","wikidata":"https://www.wikidata.org/wiki/Q2517984","display_name":"Lomax distribution","level":3,"score":0.652662456035614},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6103394031524658},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.5820394158363342},{"id":"https://openalex.org/C190373308","wikidata":"https://www.wikidata.org/wiki/Q837683","display_name":"Pareto distribution","level":2,"score":0.48643064498901367},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4291606843471527},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3858509361743927},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15793585777282715},{"id":"https://openalex.org/C133514767","wikidata":"https://www.wikidata.org/wiki/Q5532448","display_name":"Generalized Pareto distribution","level":3,"score":0.1399242877960205},{"id":"https://openalex.org/C147581598","wikidata":"https://www.wikidata.org/wiki/Q729429","display_name":"Extreme value theory","level":2,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/adprl.2014.7010619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010619","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:839862","is_oa":false,"landing_page_url":"http://library.tue.nl/csp/dare/LinkToRepository.csp?recordnumber=839862","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:839862","is_oa":false,"landing_page_url":"http://repository.tue.nl/839862","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:889210","is_oa":false,"landing_page_url":"http://repository.tue.nl/889210","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:vubissmart:VUBISSMART:2000:90596","is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/annealingpareto-multiobjective-multiarmed-bandit-algorithm(37a6486b-ad49-4439-831a-fcb713a2576e).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:oai:vubissmart:VUBISSMART:2000:90597","is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/annealingpareto-multiobjective-multiarmed-bandit-algorithm(4ba8234c-71b3-4faa-b069-3007a3a63b86).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":"","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1485231155","https://openalex.org/W1526354953","https://openalex.org/W1911551976","https://openalex.org/W1963665823","https://openalex.org/W1979559241","https://openalex.org/W2039522160","https://openalex.org/W2069034916","https://openalex.org/W2095602422","https://openalex.org/W2098907614","https://openalex.org/W2108738385","https://openalex.org/W2168405694","https://openalex.org/W2397940186","https://openalex.org/W2499226730","https://openalex.org/W2949186496","https://openalex.org/W6639904974","https://openalex.org/W6676077707","https://openalex.org/W6712229319"],"related_works":["https://openalex.org/W3089681648","https://openalex.org/W3130787283","https://openalex.org/W3133591683","https://openalex.org/W2058192020","https://openalex.org/W2123147238","https://openalex.org/W2784013114","https://openalex.org/W2460452048","https://openalex.org/W2047437401","https://openalex.org/W2245291307","https://openalex.org/W2604318887"],"abstract_inverted_index":{"In":[0,111],"the":[1,48,59,69,101,107,126,137,160,165,176,188,200,203],"stochastic":[2,13],"multi-objective":[3,192],"multi-armed":[4],"bandit":[5],"(or":[6,83,92],"MOMAB),":[7],"arms":[8,41,71,168],"generate":[9],"a":[10,20,25,37,55,143],"vector":[11],"of":[12,19,39,44],"rewards,":[14],"one":[15,31],"per":[16],"objective,":[17],"instead":[18],"single":[21],"scalar":[22],"reward.":[23],"As":[24],"result,":[26],"there":[27,35,53],"is":[28,36,54,202],"not":[29],"only":[30],"optimal":[32,40,60,70,167],"arm,":[33],"but":[34],"set":[38,62],"(Pareto":[42],"front)":[43],"reward":[45],"vectors":[46],"using":[47,142],"Pareto":[49,80,88,108,116,121,127,153,166,171,177,184],"dominance":[50,109,122,154,172],"relation":[51,123,173],"and":[52,64,77,103,139,169,187,196],"trade-off":[56,74],"between":[57,75,136],"finding":[58],"arm":[61],"(exploration)":[63],"selecting":[65],"fairly":[66],"or":[67,87],"evenly":[68],"(exploitation).":[72],"To":[73],"exploration":[76,138],"exploitation,":[78],"either":[79],"knowledge":[81],"gradient":[82],"Pareto-KG":[84],"for":[85,94],"short),":[86],"upper":[89],"confidence":[90],"bound":[91],"Pareto-UCB1":[93],"short)":[95],"can":[96],"be":[97],"used.":[98],"They":[99],"combine":[100],"KG-policy":[102],"UCB1-policy":[104],"respectively":[105],"with":[106,152],"relation.":[110,155],"this":[112],"paper,":[113],"we":[114,197],"propose":[115,131],"Thompson":[117,185],"sampling":[118,186],"that":[119,134,199],"uses":[120,159,170],"to":[124,163,174],"find":[125],"front.":[128,178],"We":[129,179],"also":[130],"annealing-Pareto":[132,157,189,201],"algorithm":[133,158],"trades-off":[135],"exploitation":[140],"by":[141],"decaying":[144,161],"parameter":[145,162],"\u03f5":[146],"<sub":[147],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[148],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">t</sub>":[149],"in":[150],"combination":[151],"The":[156],"explore":[164],"exploit":[175],"experimentally":[180],"compare":[181],"Pareto-KG,":[182],"Pareto-UCB1,":[183],"algorithms":[190],"on":[191],"Bernoulli":[193],"distribution":[194],"problems":[195],"conclude":[198],"best":[204],"performing":[205],"algorithm.":[206]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
