{"id":"https://openalex.org/W4377000567","doi":"https://doi.org/10.1109/tac.2023.3277309","title":"Equivalence of Optimality Criteria for Markov Decision Process and Model Predictive Control","display_name":"Equivalence of Optimality Criteria for Markov Decision Process and Model Predictive Control","publication_year":2023,"publication_date":"2023-05-17","ids":{"openalex":"https://openalex.org/W4377000567","doi":"https://doi.org/10.1109/tac.2023.3277309"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2023.3277309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2023.3277309","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/A5033874726","display_name":"Arash Bahari Kordabad","orcid":"https://orcid.org/0000-0001-8931-5372"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Arash Bahari Kordabad","raw_affiliation_strings":["Department of Engineering Cybernetics, Norwegian University of Science and Technology, Trondheim, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Cybernetics, Norwegian University of Science and Technology, Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106707940","display_name":"Mario Zanon","orcid":"https://orcid.org/0000-0001-5925-0440"},"institutions":[{"id":"https://openalex.org/I127077003","display_name":"IMT School for Advanced Studies Lucca","ror":"https://ror.org/035gh3a49","country_code":"IT","type":"education","lineage":["https://openalex.org/I127077003"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mario Zanon","raw_affiliation_strings":["IMT School for Advanced Studies, Lucca, Italy"],"affiliations":[{"raw_affiliation_string":"IMT School for Advanced Studies, Lucca, Italy","institution_ids":["https://openalex.org/I127077003"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049645185","display_name":"S\u00e9bastien Gros","orcid":"https://orcid.org/0000-0001-6054-2133"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Sebastien Gros","raw_affiliation_strings":["Department of Engineering Cybernetics, Norwegian University of Science and Technology, Trondheim, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Cybernetics, Norwegian University of Science and Technology, Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033874726"],"corresponding_institution_ids":["https://openalex.org/I204778367"],"apc_list":null,"apc_paid":null,"fwci":1.5025,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.8182953,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"69","issue":"2","first_page":"1149","last_page":"1156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9962000250816345,"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/T10142","display_name":"Formal Methods in Verification","score":0.9824000000953674,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8611027002334595},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.8179978132247925},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.7505863308906555},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.7016974687576294},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.6338474750518799},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6245757341384888},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5946804285049438},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.525823712348938},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5113298296928406},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.511275053024292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5068333745002747},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4838941991329193},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.41582149267196655},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.38785356283187866},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3638821840286255},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2926476299762726},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1903771460056305},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11603835225105286},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10832399129867554}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8611027002334595},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.8179978132247925},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.7505863308906555},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.7016974687576294},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.6338474750518799},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6245757341384888},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5946804285049438},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.525823712348938},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5113298296928406},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.511275053024292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5068333745002747},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4838941991329193},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.41582149267196655},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38785356283187866},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3638821840286255},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2926476299762726},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1903771460056305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11603835225105286},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10832399129867554},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2023.3277309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2023.3277309","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":[{"score":0.75,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323299","display_name":"Norges Forskningsr\u00e5d","ror":"https://ror.org/00epmv149"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1982650427","https://openalex.org/W2098432798","https://openalex.org/W2101915445","https://openalex.org/W2161040592","https://openalex.org/W2529970964","https://openalex.org/W2591650635","https://openalex.org/W2930426397","https://openalex.org/W2948652605","https://openalex.org/W3015341440","https://openalex.org/W3100789280","https://openalex.org/W3128368486","https://openalex.org/W3136876223","https://openalex.org/W3138294267","https://openalex.org/W3169649074","https://openalex.org/W3185747626","https://openalex.org/W4213251304","https://openalex.org/W4285379000","https://openalex.org/W4285446252","https://openalex.org/W4294597284","https://openalex.org/W4296849093","https://openalex.org/W4298023569","https://openalex.org/W6634104297","https://openalex.org/W6684205842"],"related_works":["https://openalex.org/W2049472152","https://openalex.org/W1974307281","https://openalex.org/W2152670157","https://openalex.org/W4308702637","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2903299703","https://openalex.org/W1859185863","https://openalex.org/W2016648086","https://openalex.org/W2808418668"],"abstract_inverted_index":{"This":[0,38,81],"article":[1],"shows":[2],"that":[3],"the":[4,52,78,92,106,112],"optimal":[5,27],"policy":[6],"and":[7,48,120],"value":[8],"functions":[9],"of":[10,59],"a":[11,24,44,62,69],"Markov":[12],"decision":[13],"process":[14],"(MDP),":[15],"either":[16],"discounted":[17],"or":[18],"not,":[19],"can":[20,39,100],"be":[21,40,102],"captured":[22],"by":[23,42],"finite-horizon":[25],"undiscounted":[26],"control":[28,65],"problem":[29],"(OCP),":[30],"even":[31],"if":[32],"based":[33],"on":[34],"an":[35,87,117],"inexact":[36],"model.":[37],"achieved":[41],"selecting":[43],"proper":[45],"stage":[46],"cost":[47,50,93],"terminal":[49],"for":[51],"OCP.":[53],"A":[54],"very":[55],"useful":[56],"particular":[57],"case":[58,119],"OCP":[60],"is":[61,74],"model":[63,73],"predictive":[64],"(MPC)":[66],"scheme":[67,89],"where":[68],"deterministic":[70],"(possibly":[71],"nonlinear)":[72],"used":[75,103],"to":[76,85,104],"reduce":[77],"computational":[79],"complexity.":[80],"observation":[82],"leads":[83],"us":[84],"parameterize":[86],"MPC":[88,108],"fully,":[90],"including":[91],"function.":[94],"In":[95],"practice,":[96],"reinforcement":[97],"learning":[98],"algorithms":[99],"then":[101],"tune":[105],"parameterized":[107],"scheme.":[109],"We":[110],"verify":[111],"developed":[113],"theorems":[114],"analytically":[115],"in":[116,127],"LQR":[118],"we":[121],"investigate":[122],"some":[123],"other":[124],"nonlinear":[125],"examples":[126],"simulations.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}