{"id":"https://openalex.org/W7117454597","doi":"https://doi.org/10.1007/s13235-025-00693-9","title":"Model-Agnostic Hessian-Free Meta-policy Optimization via Zeroth-Order Estimation: A Linear Quadratic Regulator Perspective","display_name":"Model-Agnostic Hessian-Free Meta-policy Optimization via Zeroth-Order Estimation: A Linear Quadratic Regulator Perspective","publication_year":2025,"publication_date":"2025-12-29","ids":{"openalex":"https://openalex.org/W7117454597","doi":"https://doi.org/10.1007/s13235-025-00693-9"},"language":"en","primary_location":{"id":"doi:10.1007/s13235-025-00693-9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s13235-025-00693-9","pdf_url":null,"source":{"id":"https://openalex.org/S2502731256","display_name":"Dynamic Games and Applications","issn_l":"2153-0785","issn":["2153-0785","2153-0793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320186","host_organization_name":"Birkh\u00e4user","host_organization_lineage":["https://openalex.org/P4310320186","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Birkh\u00e4user","Springer Science+Business Media"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Dynamic Games and Applications","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/A5049094147","display_name":"Yunian Pan","orcid":"https://orcid.org/0000-0002-7277-3657"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yunian Pan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, New York University, Brooklyn, NY, 11201, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, New York University, Brooklyn, NY, 11201, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121449694","display_name":"Tao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tao Li","raw_affiliation_strings":["Department of Systems Engineering, City University of Hong Kong, Hong Kong, 999077, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering, City University of Hong Kong, Hong Kong, 999077, Hong Kong SAR, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112788004","display_name":"Quanyan Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quanyan Zhu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, New York University, Brooklyn, NY, 11201, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, New York University, Brooklyn, NY, 11201, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049094147"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":1.3703,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87179908,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"16","issue":"1","first_page":"386","last_page":"425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.29179999232292175,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.29179999232292175,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.17730000615119934,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.14499999582767487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.576200008392334},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5425000190734863},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5418000221252441},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.5080000162124634},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.49459999799728394},{"id":"https://openalex.org/keywords/ergodic-theory","display_name":"Ergodic theory","score":0.46380001306533813},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4571000039577484},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.40149998664855957},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.3765999972820282}],"concepts":[{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.576200008392334},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.573199987411499},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5425000190734863},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5418000221252441},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5285999774932861},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.5080000162124634},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.49459999799728394},{"id":"https://openalex.org/C122044880","wikidata":"https://www.wikidata.org/wiki/Q5498822","display_name":"Ergodic theory","level":2,"score":0.46380001306533813},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.40149998664855957},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39239999651908875},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.35589998960494995},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C162838799","wikidata":"https://www.wikidata.org/wiki/Q596077","display_name":"Counterexample","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C204495892","wikidata":"https://www.wikidata.org/wiki/Q1798304","display_name":"Linear-quadratic-Gaussian control","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C6929976","wikidata":"https://www.wikidata.org/wiki/Q3771881","display_name":"Regulator","level":3,"score":0.27250000834465027},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.26579999923706055},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s13235-025-00693-9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s13235-025-00693-9","pdf_url":null,"source":{"id":"https://openalex.org/S2502731256","display_name":"Dynamic Games and Applications","issn_l":"2153-0785","issn":["2153-0785","2153-0793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320186","host_organization_name":"Birkh\u00e4user","host_organization_lineage":["https://openalex.org/P4310320186","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Birkh\u00e4user","Springer Science+Business Media"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Dynamic Games and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494085563","https://openalex.org/W1873595945","https://openalex.org/W2012117977","https://openalex.org/W2022760140","https://openalex.org/W2137825550","https://openalex.org/W2492629073","https://openalex.org/W3081147848","https://openalex.org/W3098412154","https://openalex.org/W3136297071","https://openalex.org/W3163842339","https://openalex.org/W3203485495","https://openalex.org/W4241811150","https://openalex.org/W4285139567","https://openalex.org/W4285792603","https://openalex.org/W4289645239","https://openalex.org/W4289768564","https://openalex.org/W4319163914","https://openalex.org/W4367841446","https://openalex.org/W4382404262","https://openalex.org/W4382935715","https://openalex.org/W4383097437","https://openalex.org/W4386260484","https://openalex.org/W4389665716","https://openalex.org/W4391020659","https://openalex.org/W4391021288","https://openalex.org/W4404304984","https://openalex.org/W4407951851"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-21T06:30:42.041108","created_date":"2025-12-29T00:00:00"}