{"id":"https://openalex.org/W3186637586","doi":"https://doi.org/10.23919/acc50511.2021.9483085","title":"Online Learning with Implicit Exploration in Episodic Markov Decision Processes","display_name":"Online Learning with Implicit Exploration in Episodic Markov Decision Processes","publication_year":2021,"publication_date":"2021-05-25","ids":{"openalex":"https://openalex.org/W3186637586","doi":"https://doi.org/10.23919/acc50511.2021.9483085","mag":"3186637586"},"language":"en","primary_location":{"id":"doi:10.23919/acc50511.2021.9483085","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc50511.2021.9483085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101793459","display_name":"Mahsa Ghasemi","orcid":"https://orcid.org/0000-0003-4302-4806"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahsa Ghasemi","raw_affiliation_strings":["Department of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036900440","display_name":"Abolfazl Hashemi","orcid":"https://orcid.org/0000-0002-8421-4270"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abolfazl Hashemi","raw_affiliation_strings":["Oden Institute for Computational Engineering and Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oden Institute for Computational Engineering and Sciences","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067602750","display_name":"Haris Vikalo","orcid":"https://orcid.org/0000-0002-7945-4114"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haris Vikalo","raw_affiliation_strings":["Department of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068441112","display_name":"Ufuk Topcu","orcid":"https://orcid.org/0000-0003-0819-9985"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ufuk Topcu","raw_affiliation_strings":["Department of Aerospace Engineering and Engineering Mechanics, Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aerospace Engineering and Engineering Mechanics, Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":null,"first_page":"1953","last_page":"1958"},"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":0.9987999796867371,"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":0.9962999820709229,"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/regret","display_name":"Regret","score":0.7223093509674072},{"id":"https://openalex.org/keywords/hindsight-bias","display_name":"Hindsight bias","score":0.6727641224861145},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6269496083259583},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.580281674861908},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5441629886627197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5340161919593811},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5111001133918762},{"id":"https://openalex.org/keywords/sublinear-function","display_name":"Sublinear function","score":0.4736146628856659},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.461993008852005},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4255933463573456},{"id":"https://openalex.org/keywords/nondeterministic-algorithm","display_name":"Nondeterministic algorithm","score":0.42546629905700684},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.37653201818466187},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.26070308685302734},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2028711438179016},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.13010019063949585},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11419042944908142},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10594195127487183}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7223093509674072},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.6727641224861145},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6269496083259583},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.580281674861908},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5441629886627197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5340161919593811},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5111001133918762},{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.4736146628856659},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.461993008852005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4255933463573456},{"id":"https://openalex.org/C176181172","wikidata":"https://www.wikidata.org/wiki/Q3490301","display_name":"Nondeterministic algorithm","level":2,"score":0.42546629905700684},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.37653201818466187},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26070308685302734},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2028711438179016},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.13010019063949585},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11419042944908142},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10594195127487183},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc50511.2021.9483085","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc50511.2021.9483085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.800000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4908315546","display_name":null,"funder_award_id":"D19AP00004","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7377845663","display_name":null,"funder_award_id":"FA9550-19-1-0169","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W100039866","https://openalex.org/W1499669280","https://openalex.org/W1567921001","https://openalex.org/W1570963478","https://openalex.org/W1849095486","https://openalex.org/W1850488217","https://openalex.org/W2074680702","https://openalex.org/W2093825590","https://openalex.org/W2098432798","https://openalex.org/W2100415632","https://openalex.org/W2119567691","https://openalex.org/W2150234726","https://openalex.org/W2156211713","https://openalex.org/W2157016390","https://openalex.org/W2241126168","https://openalex.org/W2513180554","https://openalex.org/W2765892966","https://openalex.org/W2909648661","https://openalex.org/W2946284958","https://openalex.org/W2946500988","https://openalex.org/W2964054583","https://openalex.org/W2970795541","https://openalex.org/W2991935368","https://openalex.org/W3020125231","https://openalex.org/W3186637586","https://openalex.org/W4294183581","https://openalex.org/W4298116021","https://openalex.org/W4307347247","https://openalex.org/W6604079820","https://openalex.org/W6638777087","https://openalex.org/W6639039794","https://openalex.org/W6650205757","https://openalex.org/W6675285147","https://openalex.org/W6681980492","https://openalex.org/W6690381995","https://openalex.org/W6736209634","https://openalex.org/W6762773404","https://openalex.org/W6762889291","https://openalex.org/W6770823388","https://openalex.org/W6798977809"],"related_works":["https://openalex.org/W2172596127","https://openalex.org/W1486879240","https://openalex.org/W3096083037","https://openalex.org/W2276878381","https://openalex.org/W3166490809","https://openalex.org/W3127467241","https://openalex.org/W2000850397","https://openalex.org/W3186637586","https://openalex.org/W2095280533","https://openalex.org/W2726196000"],"abstract_inverted_index":{"A":[0],"wide":[1],"range":[2],"of":[3,11,47,128,165,186,206,217,228],"applications":[4],"require":[5],"autonomous":[6,20],"agents":[7],"that":[8,116,155,171],"are":[9],"capable":[10],"learning":[12,48],"an":[13,19,49,56,63,70,93,122,161],"a":[14,36,50,80,107,125,136,151,183],"priori":[15,51],"unknown":[16,84],"task.":[17,38],"Additionally,":[18],"agent":[21,64,87,105],"may":[22,90],"be":[23],"put":[24],"in":[25,55,92,101,147],"the":[26,45,86,104,112,131,144,166,172,204,215,226],"same":[27],"environment":[28],"multiple":[29],"times,":[30],"each":[31,102,207],"time":[32,119],"having":[33],"to":[34,85,98,111,134,143],"learn":[35,135],"different":[37],"Motivated":[39],"by":[40,69,79],"these":[41],"applications,":[42],"we":[43,61],"study":[44],"problem":[46],"and":[52,179,219],"evolving":[53],"task":[54],"online":[57,157],"manner.":[58],"In":[59],"particular,":[60],"consider":[62],"whose":[65],"behavior":[66],"is":[67,83,133,203,214,225],"modeled":[68],"episodic":[71],"Markov":[72],"decision":[73],"process.":[74],"The":[75],"agent's":[76],"task,":[77],"captured":[78],"loss":[81,113,167],"function,":[82],"and,":[88],"furthermore,":[89],"change":[91],"adversarial":[94],"manner":[95],"from":[96],"episode":[97,117],"episode.":[99],"However,":[100],"episode,":[103,208],"receives":[106],"bandit":[108],"feedback":[109],"corresponding":[110],"function":[114],"at":[115],"every":[118],"it":[120],"takes":[121],"action.":[123],"Given":[124],"limited":[126],"budget":[127],"T":[129],"episodes,":[130],"objective":[132],"policy":[137,146,152],"with":[138,141,180],"minimum":[139],"regret":[140,185],"respect":[142],"best":[145],"hindsight.":[148],"We":[149,169],"propose":[150],"search":[153],"algorithm":[154,174],"employs":[156],"mirror":[158],"descent":[159],"using":[160],"optimistically":[162],"biased":[163],"estimator":[164],"function.":[168],"prove":[170],"proposed":[173],"achieves":[175],"both":[176],"on":[177],"expectation":[178],"high":[181],"probability":[182],"sublinear":[184],"~":[187],"<i":[188,193,197,210,221],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[189,194,198,211,222],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">O</i>":[190],"(\u221a{L":[191],"T|":[192],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">S</i>":[195,212],"||":[196],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">A</i>":[199,223],"|}),":[200],"where":[201],"L":[202],"length":[205],"|":[209,213,220,224],"number":[216,227],"states,":[218],"actions.":[229]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}