{"id":"https://openalex.org/W7123364013","doi":"https://doi.org/10.1109/tac.2026.3652902","title":"From Optimization to Control: Quasi-Policy Iteration","display_name":"From Optimization to Control: Quasi-Policy Iteration","publication_year":2026,"publication_date":"2026-01-12","ids":{"openalex":"https://openalex.org/W7123364013","doi":"https://doi.org/10.1109/tac.2026.3652902"},"language":null,"primary_location":{"id":"doi:10.1109/tac.2026.3652902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2026.3652902","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/A5062733845","display_name":"Mohamad Amin Sharifi Kolarijani","orcid":"https://orcid.org/0000-0002-4290-3836"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mohamad Amin Sharifi Kolarijani","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technology, Delft, CD, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-4290-3836","affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Delft, CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111396969","display_name":"Peyman Mohajerin Esfehani","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Peyman Mohajerin Esfahani","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technology, Delft, CD, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-1286-8782","affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Delft, CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05924788,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"71","issue":"6","first_page":"3880","last_page":"3893"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7577000260353088,"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":0.7577000260353088,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.06729999929666519,"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"}},{"id":"https://openalex.org/T10046","display_name":"Stability and Control of Uncertain Systems","score":0.0421999990940094,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.65420001745224},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5835000276565552},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4975999891757965},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.4733000099658966},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.45019999146461487},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.43140000104904175},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.43130001425743103},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.42730000615119934},{"id":"https://openalex.org/keywords/analogy","display_name":"Analogy","score":0.4115000069141388}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.65420001745224},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6047999858856201},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5835000276565552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5784000158309937},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4975999891757965},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.4733000099658966},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.45019999146461487},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.43140000104904175},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.43130001425743103},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C521332185","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogy","level":2,"score":0.4115000069141388},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3928999900817871},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3675000071525574},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.32010000944137573},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.31619998812675476},{"id":"https://openalex.org/C49555168","wikidata":"https://www.wikidata.org/wiki/Q176583","display_name":"Stochastic matrix","level":3,"score":0.3012999892234802},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C145242015","wikidata":"https://www.wikidata.org/wiki/Q774123","display_name":"Approximation theory","level":2,"score":0.25920000672340393}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2026.3652902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2026.3652902","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":0.7454261779785156,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1082577111","display_name":null,"funder_award_id":"TRUST-949796","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"}],"funders":[{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"control":[1,35],"algorithms":[2],"for":[3,71],"Markov":[4],"decision":[5],"processes":[6],"(MDPs)":[7],"have":[8],"been":[9],"designed":[10],"using":[11],"an":[12,96],"implicit":[13],"analogy":[14],"with":[15,105],"well-established":[16],"optimization":[17,30],"algorithms.":[18],"In":[19,42],"this":[20],"paper,":[21],"we":[22],"adopt":[23],"the":[24,52,56,72,78,83,87,110],"quasi-Newton":[25],"method":[26],"(QNM)":[27],"from":[28],"convex":[29],"to":[31,67,101,109],"introduce":[32],"a":[33,48,106],"novel":[34,49],"algorithm":[36,85],"coined":[37],"as":[38,91],"quasi-policy":[39],"iteration":[40,58],"(QPI).":[41],"particular,":[43],"QPI":[44],"is":[45],"based":[46],"on":[47,77],"approximation":[50],"of":[51,74,103],"\u201cHessian\u201d":[53],"matrix":[54],"in":[55],"policy":[57],"algorithm,":[59],"which":[60],"exploits":[61],"two":[62],"linear":[63],"structural":[64],"constraints":[65],"specific":[66],"MDPs":[68],"and":[69],"allows":[70],"incorporation":[73],"prior":[75],"information":[76],"transition":[79],"probability":[80],"kernel.":[81],"While":[82],"proposed":[84],"has":[86],"same":[88],"computational":[89],"complexity":[90],"value":[92],"iteration,":[93],"it":[94],"exhibits":[95],"empirical":[97],"convergence":[98],"behavior":[99],"similar":[100],"that":[102],"QNM":[104],"low":[107],"sensitivity":[108],"discount":[111],"factor.":[112]},"counts_by_year":[],"updated_date":"2026-05-30T06:14:24.967023","created_date":"2026-01-14T00:00:00"}