{"id":"https://openalex.org/W4410233541","doi":"https://doi.org/10.1287/moor.2023.0275","title":"Online Regret Bounds for Satisficing in Markov Decision Processes","display_name":"Online Regret Bounds for Satisficing in Markov Decision Processes","publication_year":2025,"publication_date":"2025-05-09","ids":{"openalex":"https://openalex.org/W4410233541","doi":"https://doi.org/10.1287/moor.2023.0275"},"language":"en","primary_location":{"id":"doi:10.1287/moor.2023.0275","is_oa":false,"landing_page_url":"https://doi.org/10.1287/moor.2023.0275","pdf_url":null,"source":{"id":"https://openalex.org/S55826652","display_name":"Mathematics of Operations Research","issn_l":"0364-765X","issn":["0364-765X","1526-5471"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315699","host_organization_name":"Institute for Operations Research and the Management Sciences","host_organization_lineage":["https://openalex.org/P4310315699"],"host_organization_lineage_names":["Institute for Operations Research and the Management Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Mathematics of Operations Research","raw_type":"journal-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/A5053121292","display_name":"Hossein Hajiabolhassan","orcid":"https://orcid.org/0000-0001-8146-9764"},"institutions":[{"id":"https://openalex.org/I202276237","display_name":"Medical University of Graz","ror":"https://ror.org/02n0bts35","country_code":"AT","type":"education","lineage":["https://openalex.org/I202276237"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Hossein Hajiabolhassan","raw_affiliation_strings":["Institute of Human Genetics, Diagnostic and Research Center for Molecular Biomedicine, Medical University of Graz, 8010 Graz, Austria"],"raw_orcid":"https://orcid.org/0000-0001-8146-9764","affiliations":[{"raw_affiliation_string":"Institute of Human Genetics, Diagnostic and Research Center for Molecular Biomedicine, Medical University of Graz, 8010 Graz, Austria","institution_ids":["https://openalex.org/I202276237"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031149136","display_name":"Ronald Ortner","orcid":"https://orcid.org/0000-0001-6033-2208"},"institutions":[{"id":"https://openalex.org/I182712176","display_name":"Montanuniversit\u00e4t Leoben","ror":"https://ror.org/02fhfw393","country_code":"AT","type":"education","lineage":["https://openalex.org/I182712176"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Ronald Ortner","raw_affiliation_strings":["Lehrstuhl f\u00fcr Informationstechnologie, Montanuniversit\u00e4t Leoben, 8700 Leoben, Austria"],"raw_orcid":"https://orcid.org/0000-0001-6033-2208","affiliations":[{"raw_affiliation_string":"Lehrstuhl f\u00fcr Informationstechnologie, Montanuniversit\u00e4t Leoben, 8700 Leoben, Austria","institution_ids":["https://openalex.org/I182712176"]}]}],"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":0.10259106,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"51","issue":"2","first_page":"1097","last_page":"1119"},"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":0.9984999895095825,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9968000054359436,"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/satisficing","display_name":"Satisficing","score":0.8842756748199463},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.8727046251296997},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.7770901322364807},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7513961791992188},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5562371611595154},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5454379916191101},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.4892585277557373},{"id":"https://openalex.org/keywords/decision-theory","display_name":"Decision theory","score":0.4382481873035431},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.42297685146331787},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.41759175062179565},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21393460035324097},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.19909030199050903},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.18524980545043945}],"concepts":[{"id":"https://openalex.org/C94822996","wikidata":"https://www.wikidata.org/wiki/Q1777902","display_name":"Satisficing","level":2,"score":0.8842756748199463},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8727046251296997},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7770901322364807},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7513961791992188},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5562371611595154},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5454379916191101},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.4892585277557373},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.4382481873035431},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.42297685146331787},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.41759175062179565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21393460035324097},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.19909030199050903},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.18524980545043945}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1287/moor.2023.0275","is_oa":false,"landing_page_url":"https://doi.org/10.1287/moor.2023.0275","pdf_url":null,"source":{"id":"https://openalex.org/S55826652","display_name":"Mathematics of Operations Research","issn_l":"0364-765X","issn":["0364-765X","1526-5471"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315699","host_organization_name":"Institute for Operations Research and the Management Sciences","host_organization_lineage":["https://openalex.org/P4310315699"],"host_organization_lineage_names":["Institute for Operations Research and the Management Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Mathematics of Operations Research","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2040228279","https://openalex.org/W2168405694","https://openalex.org/W2791950347","https://openalex.org/W2962677764","https://openalex.org/W2962735187","https://openalex.org/W4206530644","https://openalex.org/W4233840023","https://openalex.org/W4327630357"],"related_works":["https://openalex.org/W2970347269","https://openalex.org/W4287863949","https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1850488217","https://openalex.org/W1515117609","https://openalex.org/W4287102143","https://openalex.org/W2945119207","https://openalex.org/W1589140671"],"abstract_inverted_index":{"We":[0,42],"consider":[1],"general":[2,96],"reinforcement":[3],"learning":[4],"under":[5],"the":[6,16,64,86,100,106,128,140,146,153,160],"average":[7,31,110],"reward":[8,32,111],"criterion":[9],"in":[10],"Markov":[11],"decision":[12],"processes":[13],"(MDPs),":[14],"when":[15],"learner\u2019s":[17],"goal":[18],"is":[19,33,51,72,79,149,168],"not":[20],"to":[21,53,63,89,123,145],"learn":[22],"an":[23],"optimal":[24,107,147],"policy,":[25],"but":[26],"accepts":[27],"any":[28],"policy":[29,74,108,148],"whose":[30],"above":[34,75,112],"a":[35,73,80,94],"given":[36],"satisfaction":[37],"level":[38,65],"[Formula:":[39,66,113,124,136],"see":[40,67,114,125,137],"text].":[41,126],"show":[43],"that":[44,56,70,98],"with":[45,61,121,143],"this":[46,76,116],"more":[47,95],"modest":[48],"objective,":[49],"it":[50],"possible":[52],"give":[54],"algorithms":[55],"only":[57],"have":[58],"constant":[59],"regret":[60,120,142],"respect":[62,122,144],"text],":[68,115,138],"provided":[69],"there":[71],"level.":[77],"This":[78],"generalization":[81],"of":[82,102],"known":[83],"results":[84],"from":[85,159],"bandit":[87],"setting":[88],"MDPs.":[90],"Further,":[91],"we":[92],"present":[93],"algorithm":[97,117],"achieves":[99],"best":[101],"both":[103],"worlds:":[104],"If":[105],"has":[109,118],"bounded":[119,150],"On":[127],"other":[129],"hand,":[130],"if":[131],"all":[132],"policies":[133],"are":[134],"below":[135],"then":[139],"expected":[141],"as":[151],"for":[152],"UCRL2":[154],"algorithm.":[155],"Funding:":[156],"Financial":[157],"support":[158],"Austrian":[161],"Science":[162],"Fund":[163],"(FWF)":[164],"[Grant":[165],"TAI":[166],"590-N]":[167],"gratefully":[169],"acknowledged.":[170]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}