{"id":"https://openalex.org/W4413293830","doi":"https://doi.org/10.1137/23m1560781","title":"Policy Gradient Converges to the Globally Optimal Policy for Nearly Linear-Quadratic Regulators","display_name":"Policy Gradient Converges to the Globally Optimal Policy for Nearly Linear-Quadratic Regulators","publication_year":2025,"publication_date":"2025-08-18","ids":{"openalex":"https://openalex.org/W4413293830","doi":"https://doi.org/10.1137/23m1560781"},"language":"en","primary_location":{"id":"doi:10.1137/23m1560781","is_oa":false,"landing_page_url":"https://doi.org/10.1137/23m1560781","pdf_url":null,"source":{"id":"https://openalex.org/S897311980","display_name":"SIAM Journal on Control and Optimization","issn_l":"0363-0129","issn":["0363-0129","1095-7138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Control and Optimization","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/A5066254023","display_name":"Yinbin Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159548","display_name":"Risk Engineering (Bulgaria)","ror":"https://ror.org/051e4zg07","country_code":"BG","type":"company","lineage":["https://openalex.org/I4210159548"]}],"countries":["BG"],"is_corresponding":true,"raw_author_name":"Yinbin Han","raw_affiliation_strings":["Department of Finance and Risk Engineering, Tandon School of Engineering, New York University, Brooklyn, NY 11201 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Finance and Risk Engineering, Tandon School of Engineering, New York University, Brooklyn, NY 11201 USA","institution_ids":["https://openalex.org/I4210159548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041237539","display_name":"Meisam Razaviyayn","orcid":"https://orcid.org/0000-0003-4342-6661"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meisam Razaviyayn","raw_affiliation_strings":["Daniel J. Epstein Department of Industrial and Systems Engineering, University of Southern California, Los Angeles, CA 90089-0193 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Daniel J. Epstein Department of Industrial and Systems Engineering, University of Southern California, Los Angeles, CA 90089-0193 USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068576165","display_name":"Renyuan Xu","orcid":"https://orcid.org/0000-0003-4293-3450"},"institutions":[{"id":"https://openalex.org/I4210159548","display_name":"Risk Engineering (Bulgaria)","ror":"https://ror.org/051e4zg07","country_code":"BG","type":"company","lineage":["https://openalex.org/I4210159548"]}],"countries":["BG"],"is_corresponding":false,"raw_author_name":"Renyuan Xu","raw_affiliation_strings":["Department of Finance and Risk Engineering, Tandon School of Engineering, New York University, Brooklyn, NY 11201 USA"],"raw_orcid":"https://orcid.org/0000-0003-4293-3450","affiliations":[{"raw_affiliation_string":"Department of Finance and Risk Engineering, Tandon School of Engineering, New York University, Brooklyn, NY 11201 USA","institution_ids":["https://openalex.org/I4210159548"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066254023"],"corresponding_institution_ids":["https://openalex.org/I4210159548"],"apc_list":null,"apc_paid":null,"fwci":1.0999,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80535557,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"63","issue":"4","first_page":"2936","last_page":"2963"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9979000091552734,"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":0.9979000091552734,"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":0.9939000010490417,"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":0.9775999784469604,"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/mathematics","display_name":"Mathematics","score":0.8151884078979492},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.5567818284034729},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4516375660896301},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.38812440633773804},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3844665288925171},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.09317925572395325}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.8151884078979492},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.5567818284034729},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4516375660896301},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.38812440633773804},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3844665288925171},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.09317925572395325}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/23m1560781","is_oa":false,"landing_page_url":"https://doi.org/10.1137/23m1560781","pdf_url":null,"source":{"id":"https://openalex.org/S897311980","display_name":"SIAM Journal on Control and Optimization","issn_l":"0363-0129","issn":["0363-0129","1095-7138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Control and Optimization","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F747265653","display_name":"Google Research","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W177930832","https://openalex.org/W1561445488","https://openalex.org/W2098432798","https://openalex.org/W2166163936","https://openalex.org/W2257979135","https://openalex.org/W2802292836","https://openalex.org/W2939569248","https://openalex.org/W2965497096","https://openalex.org/W2966348706","https://openalex.org/W2995486512","https://openalex.org/W3098412154","https://openalex.org/W3141455185","https://openalex.org/W3203485495","https://openalex.org/W3209135762","https://openalex.org/W4206419526"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027","https://openalex.org/W2962838298","https://openalex.org/W2600246793"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}