乐胖代购免代理版

{"id":"https://openalex.org/W2150317779","doi":"https://doi.org/10.1109/icmla.2010.74","title":"On-Line Adaptation of Exploration in the One-Armed Bandit with Covariates Problem","display_name":"On-Line Adaptation of Exploration in the One-Armed Bandit with Covariates Problem","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W2150317779","doi":"https://doi.org/10.1109/icmla.2010.74","mag":"2150317779"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla.2010.74","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.soton.ac.uk/271615/1/PID1505865.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026098176","display_name":"Adam M. Sykulski","orcid":"https://orcid.org/0000-0002-5564-3674"},"institutions":[{"id":"https://openalex.org/I4210123447","display_name":"London Institute for Mathematical Sciences","ror":"https://ror.org/0390mzx53","country_code":"GB","type":"education","lineage":["https://openalex.org/I4210123447"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Adam M. Sykulski","raw_affiliation_strings":["Institute of Mathematical Sciences, Imperial College London, London, UK"],"affiliations":[{"raw_affiliation_string":"Institute of Mathematical Sciences, Imperial College London, London, UK","institution_ids":["https://openalex.org/I4210123447","https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001575774","display_name":"Niall M. Adams","orcid":"https://orcid.org/0000-0003-0342-0513"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Niall M. Adams","raw_affiliation_strings":["Department of Mathematics, Imperial College London, London, UK"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036583884","display_name":"Nicholas R. Jennings","orcid":"https://orcid.org/0000-0003-0166-248X"},"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":"Nicholas R. Jennings","raw_affiliation_strings":["School of Electronics and Computer Science, University of Southampton, UK"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Computer Science, University of Southampton, UK","institution_ids":["https://openalex.org/I43439940"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.069,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":10,"citation_normalized_percentile":{"value":0.852941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":84,"max":85},"biblio":{"volume":"3720","issue":null,"first_page":"459","last_page":"464"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Optimization of Multi-Armed Bandit Problems","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":"Optimization of Multi-Armed Bandit Problems","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 Algorithms","score":0.9993,"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":"Distributed Coordination in Online Robotics Research","score":0.9957,"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/bandit-optimization","display_name":"Bandit Optimization","score":0.595141},{"id":"https://openalex.org/keywords/contextual-bandits","display_name":"Contextual Bandits","score":0.534457},{"id":"https://openalex.org/keywords/online-algorithms","display_name":"Online Algorithms","score":0.51994},{"id":"https://openalex.org/keywords/multi-armed-bandit","display_name":"Multi-armed bandit","score":0.5041417}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7880598},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.76717246},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.74569756},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6386929},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6040999},{"id":"https://openalex.org/C119043178","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Covariate","level":2,"score":0.5999613},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.58600146},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.5041417},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.45433667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3559627},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3556737},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.141114},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla.2010.74","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://eprints.soton.ac.uk/271615/1/PID1505865.pdf","pdf_url":"https://eprints.soton.ac.uk/271615/1/PID1505865.pdf","source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":["University of Southampton"],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://eprints.soton.ac.uk/271615/1/PID1505865.pdf","pdf_url":"https://eprints.soton.ac.uk/271615/1/PID1505865.pdf","source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":["University of Southampton"],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.75,"display_name":"Peace, justice, and strong institutions"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":24,"referenced_works":["https://openalex.org/W1497256448","https://openalex.org/W1516061453","https://openalex.org/W1595351358","https://openalex.org/W1598539741","https://openalex.org/W1659842140","https://openalex.org/W1998498767","https://openalex.org/W2004971231","https://openalex.org/W2005311763","https://openalex.org/W2017154601","https://openalex.org/W2030729276","https://openalex.org/W2045097767","https://openalex.org/W2057050711","https://openalex.org/W2065398693","https://openalex.org/W2101046777","https://openalex.org/W2104389751","https://openalex.org/W2115519224","https://openalex.org/W2121863487","https://openalex.org/W2138859735","https://openalex.org/W2168405694","https://openalex.org/W2317700292","https://openalex.org/W2519411794","https://openalex.org/W4214717370","https://openalex.org/W4246270964","https://openalex.org/W4298215580"],"related_works":["https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W3207760230","https://openalex.org/W2536018345","https://openalex.org/W2358353312","https://openalex.org/W2353836703","https://openalex.org/W2296488620","https://openalex.org/W17155033","https://openalex.org/W1590307681","https://openalex.org/W1496222301"],"abstract_inverted_index":{"Many":[0],"sequential":[1,175],"decision":[2,176],"making":[3,177],"problems":[4,136,183],"require":[5],"an":[6],"agent":[7],"to":[8,13,31,96,127,143,155,173],"balance":[9],"exploration":[10,62,133],"and":[11,92,137],"exploitation":[12],"maximise":[14],"long-term":[15],"reward.":[16],"Existing":[17],"policies":[18],"that":[19,26,140,151],"address":[20],"this":[21,54,73],"tradeoff":[22],"typically":[23],"have":[24],"parameters":[25,45],"are":[27,46,141],"set":[28],"a":[29,77,156],"priori":[30],"control":[32,129],"the":[33,40,50,59,70,102,107,114,123,130],"amount":[34,60,103,131],"of":[35,43,61,104,125,132],"exploration.":[36],"In":[37,53],"finite-time":[38,135],"problems,":[39,178],"optimal":[41],"values":[42],"these":[44],"highly":[47],"dependent":[48],"on":[49],"problem":[51],"faced.":[52],"paper,":[55],"we":[56,75,149,165],"propose":[57],"adapting":[58],"performed":[63],"on-line,":[64],"as":[65,89,159,161,180],"information":[66],"is":[67,153],"gathered":[68],"by":[69,101],"agent.":[71],"To":[72],"end":[74],"introduce":[76],"novel":[78],"algorithm,":[79],"e-ADAPT,":[80],"which":[81,121],"has":[82],"no":[83],"free":[84],"parameters.":[85],"The":[86],"algorithm":[87],"adapts":[88],"it":[90],"plays":[91],"sequentially":[93],"chooses":[94],"whether":[95],"explore":[97],"or":[98],"exploit,":[99],"driven":[100],"uncertainty":[105],"in":[106,134],"system.":[108],"We":[109],"provide":[110],"simulation":[111],"results":[112],"for":[113],"one":[115],"armed":[116],"bandit":[117,182],"with":[118,184],"covariates":[119],"problem,":[120],"demonstrate":[122],"effectiveness":[124],"e-ADAPT":[126,152],"correctly":[128],"yield":[138],"rewards":[139],"close":[142],"optimally":[144],"tuned":[145],"off-line":[146],"policies.":[147],"Furthermore,":[148],"show":[150],"robust":[154],"high-dimensional":[157],"covariate,":[158],"well":[160],"misspecified":[162],"models.":[163],"Finally,":[164],"describe":[166],"how":[167],"our":[168],"methods":[169],"could":[170],"be":[171],"extended":[172],"other":[174],"such":[179],"dynamic":[181],"changing":[185],"reward":[186],"structures.":[187]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2150317779","counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2024-11-22T05:51:44.177718","created_date":"2016-06-24"}