{"id":"https://openalex.org/W4387246226","doi":"https://doi.org/10.1145/3626570.3626582","title":"What is an Optimal Policy in Time-Average MDP?","display_name":"What is an Optimal Policy in Time-Average MDP?","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387246226","doi":"https://doi.org/10.1145/3626570.3626582"},"language":"en","primary_location":{"id":"doi:10.1145/3626570.3626582","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626570.3626582","pdf_url":null,"source":{"id":"https://openalex.org/S4210187660","display_name":"ACM SIGMETRICS Performance Evaluation Review","issn_l":"0163-5999","issn":["0163-5999","1557-9484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMETRICS Performance Evaluation Review","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-04696993/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052639125","display_name":"Nicolas Gast","orcid":"https://orcid.org/0000-0001-6884-8698"},"institutions":[{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Nicolas Gast","raw_affiliation_strings":["Univ. Grenoble Alpes, Inria, Grenoble, France"],"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes, Inria, Grenoble, France","institution_ids":["https://openalex.org/I899635006","https://openalex.org/I4210101348"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073088518","display_name":"Bruno Gaujal","orcid":"https://orcid.org/0000-0001-9081-8401"},"institutions":[{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Bruno Gaujal","raw_affiliation_strings":["Univ. Grenoble Alpes, Inria, Grenoble, France"],"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes, Inria, Grenoble, France","institution_ids":["https://openalex.org/I899635006","https://openalex.org/I4210101348"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061766264","display_name":"Kimang Khun","orcid":"https://orcid.org/0000-0002-1939-4332"},"institutions":[{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Kimang Khun","raw_affiliation_strings":["Univ. Grenoble Alpes, Inria, Grenoble, France"],"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes, Inria, Grenoble, France","institution_ids":["https://openalex.org/I899635006","https://openalex.org/I4210101348"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052639125"],"corresponding_institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I899635006"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12937423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"51","issue":"2","first_page":"30","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9969000220298767,"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/T11182","display_name":"Auction Theory and Applications","score":0.9941999912261963,"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/value","display_name":"Value (mathematics)","score":0.5857337117195129},{"id":"https://openalex.org/keywords/connection","display_name":"Connection (principal bundle)","score":0.5719022750854492},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5413482189178467},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.49152716994285583},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43892940878868103},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4298182427883148},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4256616532802582},{"id":"https://openalex.org/keywords/optimality-criterion","display_name":"Optimality criterion","score":0.4172605872154236},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06814315915107727}],"concepts":[{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5857337117195129},{"id":"https://openalex.org/C13355873","wikidata":"https://www.wikidata.org/wiki/Q2920850","display_name":"Connection (principal bundle)","level":2,"score":0.5719022750854492},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5413482189178467},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.49152716994285583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43892940878868103},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4298182427883148},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4256616532802582},{"id":"https://openalex.org/C2778153524","wikidata":"https://www.wikidata.org/wiki/Q4241335","display_name":"Optimality criterion","level":2,"score":0.4172605872154236},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06814315915107727},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3626570.3626582","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626570.3626582","pdf_url":null,"source":{"id":"https://openalex.org/S4210187660","display_name":"ACM SIGMETRICS Performance Evaluation Review","issn_l":"0163-5999","issn":["0163-5999","1557-9484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMETRICS Performance Evaluation Review","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-04696993v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-04696993","pdf_url":"https://inria.hal.science/hal-04696993/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM SIGMETRICS Workshop MAMA, Jun 2023, Orlando (FL), United States. pp.30-32, &#x27E8;10.1145/3626570.3626582&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04696993v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-04696993","pdf_url":"https://inria.hal.science/hal-04696993/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM SIGMETRICS Workshop MAMA, Jun 2023, Orlando (FL), United States. pp.30-32, &#x27E8;10.1145/3626570.3626582&#x27E9;","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387246226.pdf","grobid_xml":"https://content.openalex.org/works/W4387246226.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W163688550","https://openalex.org/W2035451736","https://openalex.org/W2111971348","https://openalex.org/W2119567691","https://openalex.org/W4214717370","https://openalex.org/W4233840023"],"related_works":["https://openalex.org/W587735977","https://openalex.org/W1978142926","https://openalex.org/W3157395178","https://openalex.org/W184455116","https://openalex.org/W2058473748","https://openalex.org/W963756281","https://openalex.org/W2371558776","https://openalex.org/W2045569473","https://openalex.org/W2364426643","https://openalex.org/W3127098494"],"abstract_inverted_index":{"This":[0],"paper":[1],"discusses":[2],"the":[3,19,23,32],"notion":[4,24,33],"of":[5,34,51],"optimality":[6],"for":[7,67],"time-average":[8],"MDPs.":[9],"We":[10,40],"argue":[11],"that":[12,25,42,64],"while":[13],"most":[14],"authors":[15],"claim":[16],"to":[17],"use":[18],"\"average":[20],"reward\"":[21],"criteria,":[22],"is":[26,29],"implicitly":[27],"used":[28],"in":[30],"fact":[31],"what":[35],"we":[36],"call":[37],"Bellman":[38],"optimality.":[39],"show":[41],"it":[43],"does":[44],"not":[45],"coincide":[46],"with":[47,61],"other":[48],"existing":[49],"notions":[50],"optimality,":[52],"like":[53],"gain-optimality":[54],"and":[55,76],"bias-optimality":[56],"but":[57],"has":[58],"strong":[59],"connection":[60],"canonical-policies":[62],"(policies":[63],"are":[65],"optimal":[66],"any":[68],"finite":[69],"horizons)":[70],"as":[71,73],"well":[72],"value":[74],"iteration":[75],"policy":[77],"iterations":[78],"algorithms.":[79]},"counts_by_year":[],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}
