{"id":"https://openalex.org/W4390018125","doi":"https://doi.org/10.1109/tac.2023.3344870","title":"Probabilistic Framework of Howard's Policy Iteration: BML Evaluation and Robust Convergence Analysis","display_name":"Probabilistic Framework of Howard's Policy Iteration: BML Evaluation and Robust Convergence Analysis","publication_year":2023,"publication_date":"2023-12-20","ids":{"openalex":"https://openalex.org/W4390018125","doi":"https://doi.org/10.1109/tac.2023.3344870"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2023.3344870","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/tac.2023.3344870","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","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/A5057121004","display_name":"Yutian Wang","orcid":"https://orcid.org/0009-0005-0984-9777"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Yutian Wang","raw_affiliation_strings":["Department of Applied Mathematics, The Hong Kong Polytechnic University, Hong Kong, SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, The Hong Kong Polytechnic University, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036111181","display_name":"Yuan\u2010Hua Ni","orcid":"https://orcid.org/0000-0003-3984-3120"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan-Hua Ni","raw_affiliation_strings":["College of Artificial Intelligence, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073105796","display_name":"Zengqiang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengqiang Chen","raw_affiliation_strings":["College of Artificial Intelligence, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100784043","display_name":"Ji\u2010Feng Zhang","orcid":"https://orcid.org/0000-0002-0656-2886"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210120485","display_name":"Academy of Mathematics and Systems Science","ror":"https://ror.org/02jkmyk67","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210120485"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji-Feng Zhang","raw_affiliation_strings":["Key Laboratory of Systems and Control, Academy of Mathematics and Systems Science,Chinese Academy of Sciences, Beijing, China","Key Laboratory of Systems and Control, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China","School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Systems and Control, Academy of Mathematics and Systems Science,Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210120485"]},{"raw_affiliation_string":"Key Laboratory of Systems and Control, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210120485","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057121004"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":0.1258,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.37837698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"69","issue":"8","first_page":"5200","last_page":"5215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12617","display_name":"Energy, Environment, and Transportation Policies","score":0.9677000045776367,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12617","display_name":"Energy, Environment, and Transportation Policies","score":0.9677000045776367,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11052","display_name":"Energy Load and Power Forecasting","score":0.9592999815940857,"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"}},{"id":"https://openalex.org/T10007","display_name":"Monetary Policy and Economic Impact","score":0.9283000230789185,"subfield":{"id":"https://openalex.org/subfields/2000","display_name":"General Economics, Econometrics and Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6484489440917969},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5977940559387207},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5922597050666809},{"id":"https://openalex.org/keywords/martingale","display_name":"Martingale (probability theory)","score":0.5852210521697998},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5532853603363037},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5509735941886902},{"id":"https://openalex.org/keywords/stochastic-differential-equation","display_name":"Stochastic differential equation","score":0.539972186088562},{"id":"https://openalex.org/keywords/ideal","display_name":"Ideal (ethics)","score":0.5208007097244263},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.4600626528263092},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.39786645770072937},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.35043030977249146},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.08547043800354004}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6484489440917969},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5977940559387207},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5922597050666809},{"id":"https://openalex.org/C48406656","wikidata":"https://www.wikidata.org/wiki/Q534112","display_name":"Martingale (probability theory)","level":2,"score":0.5852210521697998},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5532853603363037},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5509735941886902},{"id":"https://openalex.org/C51955184","wikidata":"https://www.wikidata.org/wiki/Q1545585","display_name":"Stochastic differential equation","level":2,"score":0.539972186088562},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.5208007097244263},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.4600626528263092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39786645770072937},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.35043030977249146},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.08547043800354004},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2023.3344870","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/tac.2023.3344870","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5799999833106995,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G6033413095","display_name":null,"funder_award_id":"61973175","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7172555431","display_name":null,"funder_award_id":"62173191","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1507126399","https://openalex.org/W1513091520","https://openalex.org/W2002687012","https://openalex.org/W2005229381","https://openalex.org/W2018659593","https://openalex.org/W2020539709","https://openalex.org/W2026154367","https://openalex.org/W2028145673","https://openalex.org/W2037025184","https://openalex.org/W2042680115","https://openalex.org/W2043281212","https://openalex.org/W2050838777","https://openalex.org/W2061508005","https://openalex.org/W2072344743","https://openalex.org/W2073591687","https://openalex.org/W2108286682","https://openalex.org/W2113501460","https://openalex.org/W2140866181","https://openalex.org/W2145137020","https://openalex.org/W2165726932","https://openalex.org/W2167018969","https://openalex.org/W2245501338","https://openalex.org/W2327668930","https://openalex.org/W2743985642","https://openalex.org/W2803629276","https://openalex.org/W2901838001","https://openalex.org/W2904727539","https://openalex.org/W2936756261","https://openalex.org/W2963491588","https://openalex.org/W2964016242","https://openalex.org/W2983705688","https://openalex.org/W3005581722","https://openalex.org/W3082030075","https://openalex.org/W3103112879","https://openalex.org/W3103456419","https://openalex.org/W3104395920","https://openalex.org/W3128350768","https://openalex.org/W3172934943","https://openalex.org/W3202382720","https://openalex.org/W4212780424","https://openalex.org/W4214717370","https://openalex.org/W4229844634","https://openalex.org/W4239369248","https://openalex.org/W4292198165","https://openalex.org/W4297087551","https://openalex.org/W6604254268","https://openalex.org/W6640290305","https://openalex.org/W6679257226","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6790884171"],"related_works":["https://openalex.org/W2590472383","https://openalex.org/W2383873009","https://openalex.org/W2393580911","https://openalex.org/W2212184297","https://openalex.org/W4249985776","https://openalex.org/W177412878","https://openalex.org/W203295161","https://openalex.org/W4321845581","https://openalex.org/W2016859865","https://openalex.org/W572622356"],"abstract_inverted_index":{"This":[0],"article":[1],"aims":[2],"to":[3,24,50,120,164],"build":[4],"a":[5],"probabilistic":[6],"framework":[7],"for":[8,74,99],"Howard's":[9],"policy":[10,130,141],"iteration":[11,142],"algorithm":[12,160],"using":[13],"the":[14,51,84,90,96,115,123,129,134,139,144,150,155,158],"language":[15],"of":[16],"forward\u2013backward":[17],"stochastic":[18],"differential":[19,30],"equations":[20],"(FBSDEs).":[21],"As":[22],"opposed":[23],"conventional":[25],"formulations":[26],"based":[27],"on":[28,113,170],"partial":[29],"equations,":[31],"our":[32],"FBSDE-based":[33,136],"formulation":[34],"can":[35,88],"be":[36],"easily":[37],"implemented":[38],"by":[39,64,133],"optimizing":[40],"criteria":[41,117],"over":[42],"sample":[43],"data":[44],"and":[45,58,109,138],"is,":[46],"therefore,":[47],"less":[48],"sensitive":[49],"state":[52],"dimension.":[53],"In":[54,122,154],"particular,":[55],"both":[56,107],"on-policy":[57],"off-policy":[59],"evaluation":[60],"methods":[61],"are":[62,104,118],"discussed":[63],"constructing":[65],"different":[66],"FBSDEs.":[67],"The":[68,101],"backward-measurability-loss":[69],"criterion":[70],"is":[71,161],"then":[72],"proposed":[73,85,135,159],"solving":[75],"these":[76],"equations.":[77],"By":[78],"choosing":[79],"specific":[80],"weight":[81],"functions":[82],"in":[83],"criterion,":[86],"we":[87,126],"recover":[89],"popular":[91],"deep":[92],"BSDE":[93],"method":[94],"or":[95],"martingale":[97],"approach":[98],"BSDEs.":[100],"convergence":[102,152],"results":[103],"established":[105],"under":[106,167],"ideal":[108,124],"practical":[110,156],"conditions,":[111],"depending":[112],"whether":[114],"optimization":[116,171],"decreased":[119],"zero.":[121],"case,":[125,157],"prove":[127],"that":[128],"sequences":[131],"produced":[132],"algorithms":[137],"standard":[140],"have":[143,149],"same":[145,151],"performance":[146],"and,":[147],"thus,":[148],"rate.":[153],"still":[162],"proved":[163],"converge":[165],"robustly":[166],"mild":[168],"assumptions":[169],"errors.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}
