{"id":"https://openalex.org/W2396959124","doi":null,"title":"Learning and decisions in contextual multi-armed bandit tasks","display_name":"Learning and decisions in contextual multi-armed bandit tasks","publication_year":2015,"publication_date":"2015-11-01","ids":{"openalex":"https://openalex.org/W2396959124","mag":"2396959124"},"language":"en","primary_location":{"id":"pmh:oai:pure.mpg.de:item_3243360","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0006-B43A-E","pdf_url":"http://hdl.handle.net/21.11116/0000-0006-B43A-E","source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"37th Annual Meeting of the Cognitive Science Society (CogSci 2015): Mind, Technology and Society","raw_type":"info:eu-repo/semantics/conferenceObject"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/21.11116/0000-0006-B43A-E","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101768980","display_name":"Eric Schulz","orcid":"https://orcid.org/0000-0003-3088-0371","observed_orcids":["https://orcid.org/0000-0003-3088-0371"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eric Schulz","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3088-0371","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027297297","display_name":"Emmanouil Konstantinidis","orcid":"https://orcid.org/0000-0002-4782-0749","observed_orcids":["https://orcid.org/0000-0002-4782-0749"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emmanouil Konstantinidis","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4782-0749","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042858264","display_name":"Maarten Speekenbrink","orcid":"https://orcid.org/0000-0003-3221-1091","observed_orcids":["https://orcid.org/0000-0003-3221-1091"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maarten Speekenbrink","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3221-1091","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.6536,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.97788779,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2122","last_page":"2127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9922000169754028,"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":0.9922000169754028,"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/T10315","display_name":"Decision-Making and Behavioral Economics","score":0.0066999997943639755,"subfield":{"id":"https://openalex.org/subfields/1800","display_name":"General Decision Sciences"},"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/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/contextual-bandits","display_name":"contextual bandits","score":0.9850000143051147},{"id":"https://openalex.org/keywords/decision-making-under-uncertainty","display_name":"decision making under uncertainty","score":0.8289999961853027},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.7080000042915344},{"id":"https://openalex.org/keywords/gaussian-processes","display_name":"Gaussian processes","score":0.8809999823570251},{"id":"https://openalex.org/keywords/probability-matching","display_name":"probability matching","score":0.9779999852180481},{"id":"https://openalex.org/keywords/dynamic-environments","display_name":"dynamic environments","score":0.5759999752044678}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7049184441566467},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.640163242816925},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6307353377342224},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5876133441925049},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.5698299407958984},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5008976459503174},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4874172508716583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48435577750205994},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4809950590133667},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4793442189693451},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4494471549987793},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.43886786699295044},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.15174058079719543},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.1503714919090271},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13148337602615356},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09216353297233582},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:pure.mpg.de:item_3243360","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0006-B43A-E","pdf_url":"http://hdl.handle.net/21.11116/0000-0006-B43A-E","source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"37th Annual Meeting of the Cognitive Science Society (CogSci 2015): Mind, Technology and Society","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt0s78h2p2","doi":null,"is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/0s78h2p2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the Annual Meeting of the Cognitive Science Society, vol 37, iss 0","raw_type":"article"},{"id":"mag:2396959124","doi":null,"is_oa":false,"landing_page_url":"http://dblp.uni-trier.de/db/conf/cogsci/cogsci2015.html#SchulzKS15","pdf_url":null,"source":{"id":"https://openalex.org/S78735424","display_name":"Cognitive Science","issn_l":"0364-0213","issn":["0364-0213","1551-6709"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-c","erih-plus","jufo-2","ki-jl-2","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Cognitive Science","raw_type":null}],"best_oa_location":{"id":"pmh:oai:pure.mpg.de:item_3243360","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0006-B43A-E","pdf_url":"http://hdl.handle.net/21.11116/0000-0006-B43A-E","source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"37th Annual Meeting of the Cognitive Science Society (CogSci 2015): Mind, Technology and Society","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2396959124.pdf","grobid_xml":"https://content.openalex.org/works/W2396959124.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W610679523","https://openalex.org/W1618543586","https://openalex.org/W1746819321","https://openalex.org/W1978837788","https://openalex.org/W2084489534","https://openalex.org/W2090789917","https://openalex.org/W2111241577","https://openalex.org/W2112420033","https://openalex.org/W2115870554","https://openalex.org/W2166253248","https://openalex.org/W2166851712","https://openalex.org/W2951665052","https://openalex.org/W2953231921","https://openalex.org/W3090206535"],"related_works":["https://openalex.org/W3090206535","https://openalex.org/W2949851495","https://openalex.org/W4408806885","https://openalex.org/W4394500529","https://openalex.org/W4411569280","https://openalex.org/W3046246549","https://openalex.org/W7095240858","https://openalex.org/W4413025877","https://openalex.org/W2625190553","https://openalex.org/W2188298187"],"abstract_inverted_index":{"Contextual":[0,152],"Multi-Armed":[1,153],"Bandit":[2],"(CMAB)":[3],"tasks":[4],"are":[5,19,25,78,119],"a\\nnovel":[6],"framework":[7],"to":[8,33,92],"assess":[9],"decision":[10,58,87],"making":[11],"in":[12,67],"uncertain\\nenvironments.":[13],"In":[14,110],"a":[15,71,98,111,141],"CMAB":[16,68,113],"task,":[17],"participants":[18,47,77,118],"presented\\nwith":[20],"multiple":[21],"options":[22],"(arms)":[23],"which":[24],"characterized":[26],"by\\na":[27],"number":[28],"of":[29,100,124],"features":[30],"(context)":[31],"related":[32],"the":[34,38,45,93,101],"reward":[35,55],"as-\\nsociated":[36],"with":[37],"arms.":[39],"By":[40],"choosing":[41],"arms":[42],"repeatedly\\nand":[43],"observing":[44],"reward,":[46],"can":[48,136],"learn":[49],"about\\nthe":[50],"relation":[51],"between":[52],"context":[53],"and":[54,56,103],"improve\\ntheir":[57],"strategy.":[59],"We":[60],"present":[61],"two":[62],"studies":[63],"on":[64,144],"how\\npeople":[65],"behave":[66],"tasks.":[69],"Within":[70],"stationary":[72],"en-\\nvironment,":[73],"we":[74],"?nd":[75,116],"that":[76,117,130],"best":[79,120],"described\\nby":[80],"Thompson":[81],"Sampling-based":[82],"Gaussian":[83,125],"Process":[84,126],"mod-\\nels.":[85],"This":[86],"rule":[88],"incorporates":[89],"probability":[90],"match-\\ning":[91],"expected":[94],"outcomes":[95],"derived":[96],"from":[97],"rational\\nmodel":[99],"task":[102],"it":[104],"is":[105],"especially":[106],"well-adapted":[107],"to\\nnon-stationary":[108],"environments.":[109],"dynamic":[112],"task\\nwe":[114],"again":[115],"described":[121],"by\\nprobability":[122],"matching":[123],"expectations.\\nOur":[127],"?ndings":[128],"imply":[129],"behavior":[131],"previously":[132],"referred":[133],"to\\nas":[134],"\\\\irrational\"":[135],"actually":[137],"be":[138],"seen":[139],"as":[140],"well-adapted\\nstrategy":[142],"based":[143],"powerful":[145],"inference":[146],"algorithms.\\nKeywords:":[147],"Decision":[148],"Making,":[149],"Learning,":[150],"Exploration-\\nExploitation,":[151],"Bandits":[154]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}
