{"id":"https://openalex.org/W3000090869","doi":"https://doi.org/10.1137/19m1247395","title":"On the Minimum Pair Approach for Average Cost Markov Decision Processes with Countable Discrete Action Spaces and Strictly Unbounded Costs","display_name":"On the Minimum Pair Approach for Average Cost Markov Decision Processes with Countable Discrete Action Spaces and Strictly Unbounded Costs","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3000090869","doi":"https://doi.org/10.1137/19m1247395","mag":"3000090869"},"language":"en","primary_location":{"id":"doi:10.1137/19m1247395","is_oa":false,"landing_page_url":"https://doi.org/10.1137/19m1247395","pdf_url":null,"source":{"id":"https://openalex.org/S897311980","display_name":"SIAM Journal on Control and Optimization","issn_l":"0363-0129","issn":["0363-0129","1095-7138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Control and Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1902.10685","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014937312","display_name":"Huizhen Yu","orcid":"https://orcid.org/0000-0002-3673-0094"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Huizhen Yu","raw_affiliation_strings":["RLAI Lab, Department of Computing Science, University of Alberta, Canada"],"affiliations":[{"raw_affiliation_string":"RLAI Lab, Department of Computing Science, University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5014937312"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":1.5431,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.83719965,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"58","issue":"2","first_page":"660","last_page":"685"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.98089998960495,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.98089998960495,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9750000238418579,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9563000202178955,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.9147171378135681},{"id":"https://openalex.org/keywords/majorization","display_name":"Majorization","score":0.8417264223098755},{"id":"https://openalex.org/keywords/countable-set","display_name":"Countable set","score":0.8247085809707642},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5501953363418579},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5112252235412598},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.49188709259033203},{"id":"https://openalex.org/keywords/probability-measure","display_name":"Probability measure","score":0.44925010204315186},{"id":"https://openalex.org/keywords/markov-kernel","display_name":"Markov kernel","score":0.44208720326423645},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.4129071831703186},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.39395731687545776},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.39042729139328003},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.36021187901496887},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.3256981670856476},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.26221925020217896},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.13176503777503967},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08846661448478699}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.9147171378135681},{"id":"https://openalex.org/C2777818330","wikidata":"https://www.wikidata.org/wiki/Q1994695","display_name":"Majorization","level":2,"score":0.8417264223098755},{"id":"https://openalex.org/C110729354","wikidata":"https://www.wikidata.org/wiki/Q185478","display_name":"Countable set","level":2,"score":0.8247085809707642},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5501953363418579},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5112252235412598},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.49188709259033203},{"id":"https://openalex.org/C21031990","wikidata":"https://www.wikidata.org/wiki/Q355020","display_name":"Probability measure","level":2,"score":0.44925010204315186},{"id":"https://openalex.org/C106666656","wikidata":"https://www.wikidata.org/wiki/Q6771323","display_name":"Markov kernel","level":5,"score":0.44208720326423645},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.4129071831703186},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.39395731687545776},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.39042729139328003},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36021187901496887},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3256981670856476},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.26221925020217896},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.13176503777503967},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08846661448478699}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1137/19m1247395","is_oa":false,"landing_page_url":"https://doi.org/10.1137/19m1247395","pdf_url":null,"source":{"id":"https://openalex.org/S897311980","display_name":"SIAM Journal on Control and Optimization","issn_l":"0363-0129","issn":["0363-0129","1095-7138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Control and Optimization","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1902.10685","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.10685","pdf_url":"https://arxiv.org/pdf/1902.10685","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1902.10685","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.10685","pdf_url":"https://arxiv.org/pdf/1902.10685","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7300000190734863,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320317153","display_name":"DeepMind","ror":"https://ror.org/00971b260"},{"id":"https://openalex.org/F4320319907","display_name":"Alberta Innovates - Technology Futures","ror":"https://ror.org/00ynafe15"},{"id":"https://openalex.org/F4320325651","display_name":"Alberta Innovates","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1529558080","https://openalex.org/W1535681442","https://openalex.org/W1554655067","https://openalex.org/W1578233523","https://openalex.org/W1966208686","https://openalex.org/W1973240854","https://openalex.org/W1995713768","https://openalex.org/W2010654234","https://openalex.org/W2018546408","https://openalex.org/W2018547763","https://openalex.org/W2030544250","https://openalex.org/W2038591787","https://openalex.org/W2061026830","https://openalex.org/W2063787625","https://openalex.org/W2065284701","https://openalex.org/W2087896522","https://openalex.org/W2115558605","https://openalex.org/W2119567691","https://openalex.org/W2126905415","https://openalex.org/W2130451454","https://openalex.org/W2163872159","https://openalex.org/W2180574977","https://openalex.org/W2802739963","https://openalex.org/W2910298858","https://openalex.org/W2947183726","https://openalex.org/W3150304496"],"related_works":["https://openalex.org/W4214646115","https://openalex.org/W1503613890","https://openalex.org/W2147301465","https://openalex.org/W2016588739","https://openalex.org/W1995828591","https://openalex.org/W2568646110","https://openalex.org/W1591992921","https://openalex.org/W4213333798","https://openalex.org/W2477646633","https://openalex.org/W3118361340"],"abstract_inverted_index":{"We":[0,50,100],"consider":[1],"average":[2,92],"cost":[3,93],"Markov":[4],"decision":[5],"processes":[6],"(MDPs)":[7],"with":[8,55,72,82,156],"Borel":[9],"state":[10,34,80,160],"spaces,":[11,15],"countable,":[12],"discrete":[13],"action":[14,144],"and":[16,97,111,131,151],"strictly":[17],"unbounded":[18],"one-stage":[19,152],"costs.":[20],"For":[21],"the":[22,33,41,47,60,79,83,86,89,113,149,159],"minimum":[23,65,90,109],"pair":[24,87],"approach,":[25],"we":[26,126],"introduce":[27],"a":[28,63,68,107,118,140],"new":[29],"majorization":[30,53],"condition":[31,54],"on":[32,46,78],"transition":[35],"stochastic":[36],"kernel":[37],"in":[38,116,147],"place":[39],"of":[40,62,106,142],"commonly":[42],"required":[43],"continuity":[44],"conditions":[45],"MDP":[48],"model.":[49],"combine":[51],"this":[52],"Lusin's":[56],"theorem":[57],"to":[58,139,158],"prove":[59,127],"existence":[61],"stationary":[64,69,108,114],"pair,":[66,110,119],"i.e.,":[67],"policy":[70,115],"paired":[71],"an":[73],"invariant":[74],"probability":[75],"measure":[76],"induced":[77],"space,":[81],"property":[84],"that":[85],"attains":[88],"long-run":[91],"over":[94],"all":[95],"policies":[96],"initial":[98],"distributions.":[99],"also":[101],"establish":[102],"other":[103],"optimality":[104,130],"properties":[105],"for":[112],"such":[117],"under":[120],"additional":[121],"recurrence":[122],"or":[123],"regularity":[124],"conditions,":[125],"its":[128],"pathwise":[129],"strong":[132],"optimality.":[133],"Our":[134],"results":[135],"can":[136],"be":[137],"applied":[138],"class":[141],"countable":[143],"space":[145],"MDPs":[146],"which":[148],"dynamics":[150],"costs":[153],"are":[154],"discontinuous":[155],"respect":[157],"variable.":[161]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-01-23T00:00:00"}