{"id":"https://openalex.org/W4241757062","doi":"https://doi.org/10.23919/ecc.2013.6669310","title":"Mirror decent algorithm for a multi-armed bandit governed by a stationary finite state Markov chain","display_name":"Mirror decent algorithm for a multi-armed bandit governed by a stationary finite state Markov chain","publication_year":2013,"publication_date":"2013-07-01","ids":{"openalex":"https://openalex.org/W4241757062","doi":"https://doi.org/10.23919/ecc.2013.6669310"},"language":"en","primary_location":{"id":"doi:10.23919/ecc.2013.6669310","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ecc.2013.6669310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 European Control Conference (ECC)","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/A5048935741","display_name":"Alexander Nazin","orcid":"https://orcid.org/0000-0001-6155-7425"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Alexander Nazin","raw_affiliation_strings":["Laboratory for Adaptive and Robust Control Systems, School of Mathematical Sciences of Monash University, victoria, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory for Adaptive and Robust Control Systems, School of Mathematical Sciences of Monash University, victoria, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036133145","display_name":"Boris Miller","orcid":"https://orcid.org/0000-0002-9309-1129"},"institutions":[{"id":"https://openalex.org/I2802631561","display_name":"Australian Mathematical Sciences Institute","ror":"https://ror.org/00yn60108","country_code":"AU","type":"other","lineage":["https://openalex.org/I2802631561"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Boris Miller","raw_affiliation_strings":["School of Mathematical Sciences of Monash University, Russian Academy of Sciences, Victoria, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences of Monash University, Russian Academy of Sciences, Victoria, Australia","institution_ids":["https://openalex.org/I2802631561","https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48274736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"371","last_page":"375"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9975000023841858,"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":0.9975000023841858,"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":0.9889000058174133,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9775999784469604,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.7030662894248962},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6351163387298584},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.6095414161682129},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6023179292678833},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5931854248046875},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.5746849775314331},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5663415193557739},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5661414861679077},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.520447313785553},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.46426013112068176},{"id":"https://openalex.org/keywords/finite-state","display_name":"Finite state","score":0.4596542716026306},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.45142239332199097},{"id":"https://openalex.org/keywords/adaptive-control","display_name":"Adaptive control","score":0.45103535056114197},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.43557628989219666},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.37465906143188477},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.28153157234191895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09952923655509949},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.08673891425132751},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06704443693161011}],"concepts":[{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.7030662894248962},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6351163387298584},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.6095414161682129},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6023179292678833},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5931854248046875},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.5746849775314331},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5663415193557739},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5661414861679077},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.520447313785553},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.46426013112068176},{"id":"https://openalex.org/C2983497884","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite state","level":3,"score":0.4596542716026306},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.45142239332199097},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.45103535056114197},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.43557628989219666},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.37465906143188477},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28153157234191895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09952923655509949},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.08673891425132751},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06704443693161011},{"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/ecc.2013.6669310","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ecc.2013.6669310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 European Control Conference (ECC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2999848267","https://openalex.org/W2096013579","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W1589140671","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W4323315247","https://openalex.org/W131709709"],"abstract_inverted_index":{"This":[0],"article":[1,47],"further":[2],"develops":[3,48],"an":[4,63],"adaptive":[5,64],"approach":[6,50,65],"to":[7,29,56,79,89],"the":[8,22,39,49,57,69,81,90,95,100,106],"control":[9,82],"of":[10,18,32,71,74,87],"observable":[11,59],"Markov":[12,35,60],"chains":[13,36],"with":[14,42,84],"a":[15,30,110],"finite":[16,34],"number":[17],"states.":[19],"We":[20,93],"apply":[21],"Mirror":[23],"Descent":[24],"Randomized":[25],"Control":[26],"Algorithm":[27],"(MDRCA)":[28],"class":[31],"homogeneous":[33],"governed":[37],"by":[38],"multi-armed":[40],"bandit":[41],"unknown":[43],"mean":[44,107],"losses.":[45],"The":[46],"represented":[51],"in":[52],"[18].":[53],"As":[54],"opposed":[55],"partially":[58],"decision":[61],"process":[62],"does":[66],"not":[67],"presuppose":[68],"knowledge":[70],"probabilistic":[72],"characteristics":[73],"random":[75],"perturbations":[76],"and":[77,98],"permits":[78],"obtain":[80],"strategy":[83],"known":[85],"rate":[86],"convergence":[88],"optimal":[91],"solution.":[92],"propose":[94],"concrete":[96],"MDRCA":[97],"prove":[99],"explicit,":[101],"non-asymptotic":[102],"upper":[103],"bound":[104],"for":[105],"losses":[108],"at":[109],"given":[111],"(finite)":[112],"time":[113],"horizon.":[114],"Numerical":[115],"example":[116],"illustrates":[117],"theoretical":[118],"results.":[119]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}