{"id":"https://openalex.org/W4294690810","doi":"https://doi.org/10.23919/acc53348.2022.9867217","title":"Quasi-Newton Iteration in Deterministic Policy Gradient","display_name":"Quasi-Newton Iteration in Deterministic Policy Gradient","publication_year":2022,"publication_date":"2022-06-08","ids":{"openalex":"https://openalex.org/W4294690810","doi":"https://doi.org/10.23919/acc53348.2022.9867217"},"language":"en","primary_location":{"id":"doi:10.23919/acc53348.2022.9867217","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867217","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"conference-paper","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":false,"raw_author_name":"Arash Bahari Kordabad","raw_affiliation_strings":["Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway","Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway","institution_ids":["https://openalex.org/I204778367"]},{"raw_affiliation_string":"Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011634446","display_name":"Hossein Nejatbakhsh Esfahani","orcid":"https://orcid.org/0000-0003-3515-1645"},"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":"Hossein Nejatbakhsh Esfahani","raw_affiliation_strings":["Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway","Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway","institution_ids":["https://openalex.org/I204778367"]},{"raw_affiliation_string":"Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009821721","display_name":"Wenqi Cai","orcid":"https://orcid.org/0000-0002-2195-0203"},"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":"Wenqi Cai","raw_affiliation_strings":["Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway","Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway","institution_ids":["https://openalex.org/I204778367"]},{"raw_affiliation_string":"Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"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":["Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway","Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway","institution_ids":["https://openalex.org/I204778367"]},{"raw_affiliation_string":"Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204778367"],"apc_list":null,"apc_paid":null,"fwci":0.6748,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69954204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2124","last_page":"2129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996399998664856,"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":0.996399998664856,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12676","display_name":"Machine Learning and ELM","score":0.9940000176429749,"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/hessian-matrix","display_name":"Hessian matrix","score":0.9502769112586975},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.747223973274231},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6456912755966187},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.6283249855041504},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6229148507118225},{"id":"https://openalex.org/keywords/parametrization","display_name":"Parametrization (atmospheric modeling)","score":0.5871251821517944},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5745600461959839},{"id":"https://openalex.org/keywords/newtons-method","display_name":"Newton's method","score":0.5393021702766418},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5328078269958496},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.49580201506614685},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.4920313060283661},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4810102880001068},{"id":"https://openalex.org/keywords/quasi-newton-method","display_name":"Quasi-Newton method","score":0.47117879986763},{"id":"https://openalex.org/keywords/trust-region","display_name":"Trust region","score":0.46332117915153503},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4289623498916626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1135185956954956},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07065689563751221}],"concepts":[{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.9502769112586975},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.747223973274231},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6456912755966187},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.6283249855041504},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6229148507118225},{"id":"https://openalex.org/C202887219","wikidata":"https://www.wikidata.org/wiki/Q3895221","display_name":"Parametrization (atmospheric modeling)","level":3,"score":0.5871251821517944},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5745600461959839},{"id":"https://openalex.org/C85189116","wikidata":"https://www.wikidata.org/wiki/Q374195","display_name":"Newton's method","level":3,"score":0.5393021702766418},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5328078269958496},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.49580201506614685},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.4920313060283661},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4810102880001068},{"id":"https://openalex.org/C114954040","wikidata":"https://www.wikidata.org/wiki/Q1476018","display_name":"Quasi-Newton method","level":4,"score":0.47117879986763},{"id":"https://openalex.org/C89109886","wikidata":"https://www.wikidata.org/wiki/Q1535924","display_name":"Trust region","level":3,"score":0.46332117915153503},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4289623498916626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1135185956954956},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07065689563751221},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C178635117","wikidata":"https://www.wikidata.org/wiki/Q747499","display_name":"RADIUS","level":2,"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/C74902906","wikidata":"https://www.wikidata.org/wiki/Q1190858","display_name":"Radiative transfer","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc53348.2022.9867217","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867217","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7300000190734863,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1564755532","https://openalex.org/W1970789124","https://openalex.org/W2006808740","https://openalex.org/W2098432798","https://openalex.org/W2114537044","https://openalex.org/W2130801532","https://openalex.org/W2151568021","https://openalex.org/W2565081646","https://openalex.org/W2886474253","https://openalex.org/W2930426397","https://openalex.org/W2968296759","https://openalex.org/W3101517963","https://openalex.org/W3120070300","https://openalex.org/W3123212791","https://openalex.org/W3156316153","https://openalex.org/W4301014524","https://openalex.org/W4302570325","https://openalex.org/W6633472939","https://openalex.org/W6679257226","https://openalex.org/W6682304175","https://openalex.org/W6684205842","https://openalex.org/W6730905388","https://openalex.org/W6754297394","https://openalex.org/W6785471904"],"related_works":["https://openalex.org/W2018064504","https://openalex.org/W2032089608","https://openalex.org/W1972403003","https://openalex.org/W2352811179","https://openalex.org/W1995135523","https://openalex.org/W2996962889","https://openalex.org/W3031809678","https://openalex.org/W2082573659","https://openalex.org/W4221159909","https://openalex.org/W4294690810"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,49,71,84,102],"model-free":[4],"approximation":[5],"for":[6,48],"the":[7,10,18,28,34,39,43,53,57,75,81,90,93,97],"Hessian":[8,36,41],"of":[9,12,20,74,92],"performance":[11],"deterministic":[13],"policies":[14],"to":[15,38],"use":[16],"in":[17,27,52,83,101],"context":[19],"Reinforcement":[21],"Learning":[22],"based":[23],"on":[24],"Quasi-Newton":[25],"steps":[26],"policy":[29,58,64,99],"parameters.":[30],"We":[31,78],"show":[32],"that":[33,56],"approximate":[35],"converges":[37],"exact":[40],"at":[42],"optimal":[44],"policy,":[45],"and":[46,88],"allows":[47],"superlinear":[50],"convergence":[51,91],"learning,":[54],"provided":[55],"parametrization":[59],"is":[60],"rich.":[61],"The":[62],"natural":[63,98],"gradient":[65,100],"method":[66,95],"can":[67],"be":[68],"interpreted":[69],"as":[70],"particular":[72],"case":[73,87],"proposed":[76,94],"method.":[77],"analytically":[79],"verify":[80],"formulation":[82],"simple":[85],"linear":[86],"compare":[89],"with":[96],"nonlinear":[103],"example.":[104]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}