乐胖代购免代理版

{"id":"https://openalex.org/W2626820647","doi":"https://doi.org/10.1016/j.procs.2017.05.431","title":"An Adaptive Implementation of \u03b5-Greedy in Reinforcement Learning","display_name":"An Adaptive Implementation of \u03b5-Greedy in Reinforcement Learning","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2626820647","doi":"https://doi.org/10.1016/j.procs.2017.05.431","mag":"2626820647"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2017.05.431","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.procs.2017.05.431","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002668775","display_name":"Alexandre dos Santos Mignon","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096134","display_name":"Universidade Politecnica","ror":"https://ror.org/00tnfjj44","country_code":"MZ","type":"education","lineage":["https://openalex.org/I4210096134"]},{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR","MZ"],"is_corresponding":true,"raw_author_name":"Alexandre dos Santos Mignon","raw_affiliation_strings":["Escola Polit\u00e9cnica da Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brasil"],"affiliations":[{"raw_affiliation_string":"Escola Polit\u00e9cnica da Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brasil","institution_ids":["https://openalex.org/I4210096134","https://openalex.org/I17974374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045742554","display_name":"Ricardo Luis de Azevedo da Rocha","orcid":"https://orcid.org/0000-0001-6898-4569"},"institutions":[{"id":"https://openalex.org/I4210096134","display_name":"Universidade Politecnica","ror":"https://ror.org/00tnfjj44","country_code":"MZ","type":"education","lineage":["https://openalex.org/I4210096134"]},{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR","MZ"],"is_corresponding":false,"raw_author_name":"Ricardo Luis de Azevedo da Rocha","raw_affiliation_strings":["Escola Polit\u00e9cnica da Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brasil"],"affiliations":[{"raw_affiliation_string":"Escola Polit\u00e9cnica da Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brasil","institution_ids":["https://openalex.org/I4210096134","https://openalex.org/I17974374"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002668775"],"corresponding_institution_ids":["https://openalex.org/I4210096134","https://openalex.org/I17974374"],"apc_list":null,"apc_paid":null,"fwci":1.391,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":61,"citation_normalized_percentile":{"value":0.941712,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"109","issue":null,"first_page":"1146","last_page":"1151"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9997,"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":0.9997,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9951,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9941,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adaptive-learning","display_name":"Adaptive Learning","score":0.4262591}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.88872564},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8344816},{"id":"https://openalex.org/C126221529","wikidata":"https://www.wikidata.org/wiki/Q3116070","display_name":"Greedy randomized adaptive search procedure","level":3,"score":0.67930067},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.64631784},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5295858},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.4262591},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4206649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4143121},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4111543},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23895839},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.060099542},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2017.05.431","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2017.05.431","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":6,"referenced_works":["https://openalex.org/W1508957461","https://openalex.org/W2051903196","https://openalex.org/W2167489871","https://openalex.org/W2324283695","https://openalex.org/W4214717370","https://openalex.org/W4249116379"],"related_works":["https://openalex.org/W45904909","https://openalex.org/W4321206936","https://openalex.org/W2809828719","https://openalex.org/W2541760731","https://openalex.org/W2373750984","https://openalex.org/W2277088917","https://openalex.org/W2154172459","https://openalex.org/W2018096104","https://openalex.org/W1827895227","https://openalex.org/W1517981012"],"abstract_inverted_index":{"This":[0,18],"paper":[1],"presents":[2,73],"a":[3,66,83],"method":[4,19,72],"called":[5],"adaptive":[6,40,70],"\u03b5-greedy":[7,71],"for":[8,60],"better":[9,74],"balancing":[10],"between":[11],"exploration":[12],"and":[13,37,95],"exploitation":[14],"in":[15,65,117],"reinforcement":[16],"learning.":[17],"is":[20],"based":[21],"on":[22],"classic":[23,80],"\u03b5-greedy,":[24],"which":[25],"holds":[26],"the":[27,45,50,57,61,79,92,98,101,106,118],"value":[28,46],"of":[29,39,47,100],"\u03b5":[30,48],"statically.":[31],"The":[32,69],"solution":[33],"proposed":[34],"uses":[35],"concepts":[36],"techniques":[38],"technology":[41],"to":[42,78,90,103],"allow":[43],"controlling":[44],"during":[49],"execution.":[51],"We":[52],"present":[53],"experiments":[54],"numerically":[55],"comparing":[56],"two":[58],"methods":[59],"n-armed":[62],"bandit":[63],"problem":[64],"stationary":[67],"environment.":[68],"performance":[75],"as":[76],"compared":[77],"\u03b5-greedy.":[81],"For":[82],"nonstationary":[84],"environment,":[85],"we":[86],"use":[87],"an":[88],"algorithm":[89],"detect":[91],"change":[93],"point":[94],"adaptively":[96],"modify":[97],"state":[99],"agent":[102],"learn":[104],"from":[105],"new":[107],"rewards":[108],"received.":[109],"A":[110],"recent":[111],"related":[112],"work":[113],"was":[114],"also":[115],"evaluated":[116],"paper.":[119]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2626820647","counts_by_year":[{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-01-19T20:47:19.297750","created_date":"2017-06-23"}