{"id":"https://openalex.org/W2896280943","doi":"https://doi.org/10.1109/ijcnn.2018.8489655","title":"Comparing Multi-Armed Bandit Algorithms and Q-learning for Multiagent Action Selection: a Case Study in Route Choice","display_name":"Comparing Multi-Armed Bandit Algorithms and Q-learning for Multiagent Action Selection: a Case Study in Route Choice","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2896280943","doi":"https://doi.org/10.1109/ijcnn.2018.8489655","mag":"2896280943"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2018.8489655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","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/A5001034983","display_name":"Thiago Bell Felix de Oliveira","orcid":"https://orcid.org/0000-0002-4493-8012"},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Thiago B. F. de Oliveira","raw_affiliation_strings":["Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028225369","display_name":"Ana L. C. Bazzan","orcid":"https://orcid.org/0000-0002-2803-9607"},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Ana L. C. Bazzan","raw_affiliation_strings":["Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100634614","display_name":"Bruno C. da Silva","orcid":"https://orcid.org/0000-0002-6467-9943"},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Bruno C. da Silva","raw_affiliation_strings":["Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027755211","display_name":"Ricardo Grunitzki","orcid":null},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Ricardo Grunitzki","raw_affiliation_strings":["Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil","institution_ids":["https://openalex.org/I130442723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5001034983"],"corresponding_institution_ids":["https://openalex.org/I130442723"],"apc_list":null,"apc_paid":null,"fwci":1.2705,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.82669609,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"347","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":0.9983999729156494,"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/T12288","display_name":"Optimization and Search Problems","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.827637791633606},{"id":"https://openalex.org/keywords/multi-armed-bandit","display_name":"Multi-armed bandit","score":0.7656876444816589},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7057063579559326},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.6316870450973511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6025271415710449},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5954868197441101},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5036136507987976},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4814581274986267},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4590607285499573},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.457100510597229},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4377814829349518},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.400455117225647},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1575518250465393}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.827637791633606},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.7656876444816589},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7057063579559326},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.6316870450973511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6025271415710449},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5954868197441101},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5036136507987976},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4814581274986267},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4590607285499573},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.457100510597229},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4377814829349518},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.400455117225647},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1575518250465393},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"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/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2018.8489655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W157259654","https://openalex.org/W1996069568","https://openalex.org/W2003912133","https://openalex.org/W2011282943","https://openalex.org/W2039522160","https://openalex.org/W2056568177","https://openalex.org/W2077902449","https://openalex.org/W2108738385","https://openalex.org/W2149660380","https://openalex.org/W2168405694","https://openalex.org/W2177295793","https://openalex.org/W2187642949","https://openalex.org/W2243481542","https://openalex.org/W2495333748","https://openalex.org/W2556366151","https://openalex.org/W2572752914","https://openalex.org/W2620929994","https://openalex.org/W2764937720","https://openalex.org/W2897200624","https://openalex.org/W3100779200","https://openalex.org/W6606420716","https://openalex.org/W6665962319","https://openalex.org/W6676077707","https://openalex.org/W6686925467","https://openalex.org/W6690508177","https://openalex.org/W6731934397"],"related_works":["https://openalex.org/W2015051472","https://openalex.org/W2168501056","https://openalex.org/W2742483371","https://openalex.org/W2120009678","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W3087814763","https://openalex.org/W2357975469","https://openalex.org/W2037601570","https://openalex.org/W4383815550"],"abstract_inverted_index":{"The":[0],"multi-armed":[1],"bandit":[2],"(MAB)":[3],"problem":[4],"is":[5],"concerned":[6],"with":[7,72],"an":[8],"agent":[9,45],"choosing":[10],"which":[11],"arm":[12],"of":[13,27,63,65,86],"a":[14,37,48,77,91],"slot":[15],"machine":[16],"to":[17,21,32,59,76,89],"play":[18],"in":[19],"order":[20],"optimize":[22],"its":[23],"reward.":[24],"A":[25],"family":[26],"reinforcement":[28],"learning":[29,87],"algorithms":[30,68],"exists":[31],"tackle":[33],"this":[34,55],"problem,":[35],"including":[36],"few":[38],"variants":[39],"that":[40,93],"consider":[41],"more":[42],"than":[43],"one":[44],"(thus,":[46],"characterizing":[47],"repeated":[49,79],"game)":[50],"and":[51,69],"non-stationary":[52,78],"variants.":[53],"In":[54],"paper,":[56],"we":[57],"seek":[58],"evaluate":[60],"the":[61],"performance":[62],"some":[64],"these":[66],"MAB":[67],"compare":[70],"them":[71],"Q-learning":[73],"when":[74],"applied":[75],"game,":[80],"where":[81],"commuter":[82],"agents":[83],"face":[84],"thetask":[85],"how":[88],"choose":[90],"route":[92],"minimizes":[94],"their":[95],"travel":[96],"times.":[97]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}