{"id":"https://openalex.org/W2924486842","doi":"https://doi.org/10.1137/19m1255811","title":"A Convex Programming Approach for Discrete-Time Markov Decision Processes under the Expected Total Reward Criterion","display_name":"A Convex Programming Approach for Discrete-Time Markov Decision Processes under the Expected Total Reward Criterion","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W2924486842","doi":"https://doi.org/10.1137/19m1255811","mag":"2924486842"},"language":"en","primary_location":{"id":"doi:10.1137/19m1255811","is_oa":false,"landing_page_url":"https://doi.org/10.1137/19m1255811","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","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.08853","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052608804","display_name":"Fran\u00e7ois Dufour","orcid":"https://orcid.org/0000-0001-6653-2024"},"institutions":[{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]},{"id":"https://openalex.org/I4210166017","display_name":"Institut de Math\u00e9matiques de Bordeaux","ror":"https://ror.org/05m3r1b84","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I15057530","https://openalex.org/I4210141950","https://openalex.org/I4210160189","https://openalex.org/I4210166017"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fran\u00e7ois Dufour","raw_affiliation_strings":["Quality control and dynamic reliability","Institut de Math\u00e9matiques de Bordeaux","Institut Polytechnique de Bordeaux"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Quality control and dynamic reliability","institution_ids":[]},{"raw_affiliation_string":"Institut de Math\u00e9matiques de Bordeaux","institution_ids":["https://openalex.org/I4210166017"]},{"raw_affiliation_string":"Institut Polytechnique de Bordeaux","institution_ids":["https://openalex.org/I4210160189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080459677","display_name":"Alexandre G\u00e9nadot","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166017","display_name":"Institut de Math\u00e9matiques de Bordeaux","ror":"https://ror.org/05m3r1b84","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I15057530","https://openalex.org/I4210141950","https://openalex.org/I4210160189","https://openalex.org/I4210166017"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alexandre Genadot","raw_affiliation_strings":["Institut de Math\u00e9matiques de Bordeaux","Quality control and dynamic reliability"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut de Math\u00e9matiques de Bordeaux","institution_ids":["https://openalex.org/I4210166017"]},{"raw_affiliation_string":"Quality control and dynamic reliability","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1301,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50819096,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"58","issue":"4","first_page":"2535","last_page":"2566"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9970999956130981,"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":0.9970999956130981,"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":0.9789000153541565,"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"}},{"id":"https://openalex.org/T10768","display_name":"Electric Vehicles and Infrastructure","score":0.9639000296592712,"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/mathematics","display_name":"Mathematics","score":0.7935986518859863},{"id":"https://openalex.org/keywords/infimum-and-supremum","display_name":"Infimum and supremum","score":0.7631151676177979},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7002391815185547},{"id":"https://openalex.org/keywords/compact-space","display_name":"Compact space","score":0.6134726405143738},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.5438178181648254},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5436524748802185},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.48439985513687134},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4827417731285095},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.456944078207016},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.41803762316703796},{"id":"https://openalex.org/keywords/convex-set","display_name":"Convex set","score":0.4141165614128113},{"id":"https://openalex.org/keywords/convex-analysis","display_name":"Convex analysis","score":0.41279274225234985},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.33332476019859314},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3330910801887512},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.2246781289577484},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.1474781632423401},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.12997904419898987},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09690001606941223}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7935986518859863},{"id":"https://openalex.org/C95611797","wikidata":"https://www.wikidata.org/wiki/Q17502105","display_name":"Infimum and supremum","level":2,"score":0.7631151676177979},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7002391815185547},{"id":"https://openalex.org/C18648836","wikidata":"https://www.wikidata.org/wiki/Q381892","display_name":"Compact space","level":2,"score":0.6134726405143738},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.5438178181648254},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5436524748802185},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.48439985513687134},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4827417731285095},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.456944078207016},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.41803762316703796},{"id":"https://openalex.org/C49870271","wikidata":"https://www.wikidata.org/wiki/Q193657","display_name":"Convex set","level":4,"score":0.4141165614128113},{"id":"https://openalex.org/C12108790","wikidata":"https://www.wikidata.org/wiki/Q2234833","display_name":"Convex analysis","level":4,"score":0.41279274225234985},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.33332476019859314},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3330910801887512},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.2246781289577484},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.1474781632423401},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.12997904419898987},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09690001606941223},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":9,"locations":[{"id":"doi:10.1137/19m1255811","is_oa":false,"landing_page_url":"https://doi.org/10.1137/19m1255811","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:1903.08853","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.08853","pdf_url":"https://arxiv.org/pdf/1903.08853","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":"","raw_type":"text"},{"id":"pmh:oai:HAL:hal-02071036v2","is_oa":true,"landing_page_url":"https://hal.science/hal-02071036","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2019","raw_type":"info:eu-repo/semantics/preprint"},{"id":"pmh:oai:HAL:hal-03033727v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-03033727","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SIAM Journal on Control and Optimization, 2020, 58 (4), pp.2535-2566. &#x27E8;10.1137/19M1255811&#x27E9;","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:oskar-bordeaux.fr:20.500.12278/113174","is_oa":false,"landing_page_url":"https://oskar-bordeaux.fr/handle/20.500.12278/113174","pdf_url":null,"source":{"id":"https://openalex.org/S4306402569","display_name":"Oskar-Bordeaux (Universite de Bordeaux)","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article de revue"},{"id":"pmh:oai:oskar-bordeaux.fr:20.500.12278/191762","is_oa":false,"landing_page_url":"https://oskar-bordeaux.fr/handle/20.500.12278/191762","pdf_url":null,"source":{"id":"https://openalex.org/S4306402569","display_name":"Oskar-Bordeaux (Universite de Bordeaux)","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article de revue"},{"id":"pmh:oai:oskar-bordeaux.fr:20.500.12278/192897","is_oa":false,"landing_page_url":"https://oskar-bordeaux.fr/handle/20.500.12278/192897","pdf_url":null,"source":{"id":"https://openalex.org/S4306402569","display_name":"Oskar-Bordeaux (Universite de Bordeaux)","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Document de travail - Pr\u00e9-publication"},{"id":"pmh:oai:oskar-bordeaux.fr:20.500.12278/9414","is_oa":false,"landing_page_url":"https://oskar-bordeaux.fr/handle/20.500.12278/9414","pdf_url":null,"source":{"id":"https://openalex.org/S4306402569","display_name":"Oskar-Bordeaux (Universite de Bordeaux)","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Document de travail - Pr\u00e9-publication"},{"id":"doi:10.48550/arxiv.1903.08853","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1903.08853","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.08853","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.08853","pdf_url":"https://arxiv.org/pdf/1903.08853","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":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1571840955","https://openalex.org/W1991591460","https://openalex.org/W1991625634","https://openalex.org/W2004640191","https://openalex.org/W2018190357","https://openalex.org/W2028198084","https://openalex.org/W2033830101","https://openalex.org/W2070935253","https://openalex.org/W2093298018","https://openalex.org/W2972610230","https://openalex.org/W3203406682","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2039032100","https://openalex.org/W2376997122","https://openalex.org/W2026600343","https://openalex.org/W2478309485","https://openalex.org/W4382519084","https://openalex.org/W2391247224","https://openalex.org/W2112761337","https://openalex.org/W4311073519","https://openalex.org/W144566582","https://openalex.org/W2002037426"],"abstract_inverted_index":{"In":[0],"this":[1,52],"work,":[2],"we":[3],"study":[4],"discrete-time":[5],"Markov":[6],"decision":[7],"processes":[8],"(MDPs)":[9],"under":[10],"constraints":[11],"with":[12,158],"Borel":[13],"state":[14],"and":[15,18,68,147],"action":[16],"spaces":[17],"where":[19],"all":[20],"the":[21,25,29,36,61,64,69,82,96,105,111,114,117,125,128,131,143,167],"performance":[22],"functions":[23],"have":[24,161],"same":[26],"form":[27],"of":[28,41,54,63,107,113,119,127,133],"expected":[30],"total":[31],"reward":[32],"(ETR)":[33],"criterion":[34],"over":[35,116,130],"infinite":[37],"time":[38],"horizon.":[39],"One":[40],"our":[42,174],"objective":[43],"is":[44,93,122],"to":[45,81,124,156,172],"propose":[46],"a":[47,88,148],"convex":[48,71,83],"programming":[49],"formulation":[50],"for":[51,95],"type":[53],"MDP.":[55,97],"It":[56,98],"will":[57,99],"be":[58,100],"shown":[59,102],"that":[60,103,160],"values":[62],"constrained":[65,108],"control":[66,109],"problem":[67],"associated":[70],"program":[72,84],"coincide.":[73],"Moreover,":[74],"if":[75],"there":[76,86],"exists":[77,87],"an":[78],"optimal":[79,94],"solution":[80],"then":[85],"stationary":[89,134],"randomized":[90,120,135],"policy":[91],"which":[92],"also":[101],"in":[104,166],"framework":[106],"problems,":[110],"supremum":[112,126],"ETRs":[115,129],"set":[118,132],"policies":[121],"equal":[123],"policies.":[136],"We":[137],"consider":[138],"standard":[139],"hypotheses":[140],"such":[141],"as":[142],"so-called":[144],"continuity-compactness":[145],"conditions":[146],"Slater-type":[149],"condition.":[150],"Our":[151],"assumptions":[152],"are":[153,170],"quite":[154],"weak":[155],"deal":[157],"cases":[159],"not":[162],"yet":[163],"been":[164],"addressed":[165],"literature.":[168],"Examples":[169],"presented":[171],"illustrate":[173],"results.":[175]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2023-02-11T00:00:00"}
