{"id":"https://openalex.org/W2972691245","doi":"https://doi.org/10.1109/cdc40024.2019.9029885","title":"Solving Ergodic Markov Decision Processes and Perfect Information Zero-sum Stochastic Games by Variance Reduced Deflated Value Iteration","display_name":"Solving Ergodic Markov Decision Processes and Perfect Information Zero-sum Stochastic Games by Variance Reduced Deflated Value Iteration","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W2972691245","doi":"https://doi.org/10.1109/cdc40024.2019.9029885","mag":"2972691245"},"language":"en","primary_location":{"id":"doi:10.1109/cdc40024.2019.9029885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9029885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1909.06185","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078804236","display_name":"Marianne Akian","orcid":"https://orcid.org/0000-0002-8569-7622"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Marianne Akian","raw_affiliation_strings":["INRIA and CMAP, \u00c9cole polytechnique, Palaiseau Cedex, France","French Institute for Research in Computer Science and Automation"],"affiliations":[{"raw_affiliation_string":"INRIA and CMAP, \u00c9cole polytechnique, Palaiseau Cedex, France","institution_ids":["https://openalex.org/I142476485","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"French Institute for Research in Computer Science and Automation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082671255","display_name":"St\u00e9phane Gaubert","orcid":"https://orcid.org/0000-0002-2777-9988"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Stephane Gaubert","raw_affiliation_strings":["INRIA and CMAP, \u00c9cole polytechnique, Palaiseau Cedex, France","French Institute for Research in Computer Science and Automation"],"affiliations":[{"raw_affiliation_string":"INRIA and CMAP, \u00c9cole polytechnique, Palaiseau Cedex, France","institution_ids":["https://openalex.org/I142476485","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"French Institute for Research in Computer Science and Automation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044349979","display_name":"Zheng Qu","orcid":"https://orcid.org/0000-0003-0883-2277"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]}],"countries":["CN","FR","HK"],"is_corresponding":false,"raw_author_name":"Zheng Qu","raw_affiliation_strings":["Dep. Math., The University of Hong Kong, Hong Kong","Ecole Polytechnique"],"affiliations":[{"raw_affiliation_string":"Dep. Math., The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]},{"raw_affiliation_string":"Ecole Polytechnique","institution_ids":["https://openalex.org/I142476485"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085860988","display_name":"Omar Saadi","orcid":"https://orcid.org/0000-0001-6924-954X"},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["FR","HK"],"is_corresponding":false,"raw_author_name":"Omar Saadi","raw_affiliation_strings":["INRIA and CMAP, \u00c9cole polytechnique, Palaiseau Cedex, France","UNIVERSITY OF HONG KONG"],"affiliations":[{"raw_affiliation_string":"INRIA and CMAP, \u00c9cole polytechnique, Palaiseau Cedex, France","institution_ids":["https://openalex.org/I142476485","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"UNIVERSITY OF HONG KONG","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078804236"],"corresponding_institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I142476485"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10531153,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"5963","last_page":"5970"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9828000068664551,"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":0.9828000068664551,"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/T11413","display_name":"Risk and Portfolio Optimization","score":0.9804999828338623,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9787999987602234,"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/markov-decision-process","display_name":"Markov decision process","score":0.8414312601089478},{"id":"https://openalex.org/keywords/ergodic-theory","display_name":"Ergodic theory","score":0.7418910264968872},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6727045178413391},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6647771000862122},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5996479392051697},{"id":"https://openalex.org/keywords/zero-sum-game","display_name":"Zero-sum game","score":0.5820043683052063},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5746567845344543},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5617454648017883},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.535280168056488},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4549309015274048},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.4333254098892212},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4170913100242615},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.36262595653533936},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.21290677785873413},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.08607307076454163},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.0806000828742981},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.06067976355552673}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8414312601089478},{"id":"https://openalex.org/C122044880","wikidata":"https://www.wikidata.org/wiki/Q5498822","display_name":"Ergodic theory","level":2,"score":0.7418910264968872},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6727045178413391},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6647771000862122},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5996479392051697},{"id":"https://openalex.org/C136356330","wikidata":"https://www.wikidata.org/wiki/Q156612","display_name":"Zero-sum game","level":3,"score":0.5820043683052063},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5746567845344543},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5617454648017883},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.535280168056488},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4549309015274048},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.4333254098892212},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4170913100242615},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.36262595653533936},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.21290677785873413},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.08607307076454163},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.0806000828742981},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.06067976355552673},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cdc40024.2019.9029885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9029885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1909.06185","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.06185","pdf_url":"https://arxiv.org/pdf/1909.06185","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"},{"id":"pmh:oai:HAL:hal-02423846v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-02423846","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":"CDC 2019 - 58th IEEE Conference on Decision and Control, Dec 2019, Nice, France","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.1909.06185","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1909.06185","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1909.06185","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.06185","pdf_url":"https://arxiv.org/pdf/1909.06185","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":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324478","display_name":"Fondation Math\u00e9matique Jacques Hadamard","ror":"https://ror.org/0153me927"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2972691245.pdf","grobid_xml":"https://content.openalex.org/works/W2972691245.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1480317510","https://openalex.org/W1800710304","https://openalex.org/W1859215999","https://openalex.org/W1960239420","https://openalex.org/W2077767509","https://openalex.org/W2078268196","https://openalex.org/W2081287319","https://openalex.org/W2086671299","https://openalex.org/W2119567691","https://openalex.org/W2292613520","https://openalex.org/W2486403688","https://openalex.org/W2544731027","https://openalex.org/W2575731723","https://openalex.org/W2607910526","https://openalex.org/W2765892966","https://openalex.org/W2805861379","https://openalex.org/W2963872309","https://openalex.org/W4239900517","https://openalex.org/W6638150350","https://openalex.org/W6639034510","https://openalex.org/W6752368512"],"related_works":["https://openalex.org/W2128670912","https://openalex.org/W3198596521","https://openalex.org/W4287640753","https://openalex.org/W1923338350","https://openalex.org/W2133764300","https://openalex.org/W2972691245","https://openalex.org/W3010710985","https://openalex.org/W3140738360","https://openalex.org/W1910823034","https://openalex.org/W2972903854"],"abstract_inverted_index":{"Recently,":[0],"Sidford,":[1],"Wang,":[2],"Wu":[3],"and":[4,48,72,123],"Ye":[5],"(2018)":[6],"developed":[7,114],"an":[8],"algorithm":[9,24,106],"combining":[10],"variance":[11],"reduction":[12,82],"techniques":[13,113,127],"with":[14,97],"value":[15],"iteration":[16],"to":[17,40,88],"solve":[18],"discounted":[19,90,121],"Markov":[20,45],"decision":[21,46],"processes.":[22],"This":[23],"has":[25],"a":[26,62,81,93,98],"sublinear":[27,56],"complexity":[28,57,102],"when":[29],"the":[30,84,89,109,112,120,131],"discount":[31],"factor":[32],"is":[33,61,66,78],"fixed.":[34],"Here,":[35],"we":[36],"extend":[37],"this":[38,105],"approach":[39],"mean-payoff":[41],"problems,":[42],"including":[43],"both":[44],"processes":[47],"perfect":[49],"information":[50],"zero-sum":[51],"stochastic":[52],"games.":[53],"We":[54],"obtain":[55],"bounds,":[58],"assuming":[59],"there":[60],"distinguished":[63],"state":[64],"which":[65],"accessible":[67],"from":[68,83],"all":[69,74],"initial":[70],"states":[71],"for":[73],"policies.":[75],"Our":[76],"method":[77],"based":[79],"on":[80],"mean":[85],"payoff":[86],"problem":[87,91],"by":[92,115],"Doob":[94],"h-transform,":[95],"combined":[96],"deflation":[99],"technique.":[100],"The":[101],"analysis":[103],"of":[104,130],"uses":[107],"at":[108],"same":[110],"time":[111],"Sidford":[116],"et":[117],"al.":[118],"in":[119],"case":[122],"non-linear":[124],"spectral":[125],"theory":[126],"(Collatz-Wielandt":[128],"characterization":[129],"eigenvalue).":[132]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}