{"id":"https://openalex.org/W3164660575","doi":"https://doi.org/10.1109/lcsys.2022.3172242","title":"Finite-Sample Analysis of Off-Policy Natural Actor\u2013Critic With Linear Function Approximation","display_name":"Finite-Sample Analysis of Off-Policy Natural Actor\u2013Critic With Linear Function Approximation","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3164660575","doi":"https://doi.org/10.1109/lcsys.2022.3172242","mag":"3164660575"},"language":"en","primary_location":{"id":"doi:10.1109/lcsys.2022.3172242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2022.3172242","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"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 Control Systems Letters","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/A5058269077","display_name":"Zaiwei Chen","orcid":"https://orcid.org/0000-0001-9915-5595"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zaiwei Chen","raw_affiliation_strings":["School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9915-5595","affiliations":[{"raw_affiliation_string":"School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045270609","display_name":"Sajad Khodadadian","orcid":"https://orcid.org/0000-0002-5197-4652"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sajad Khodadadian","raw_affiliation_strings":["School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5197-4652","affiliations":[{"raw_affiliation_string":"School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021806638","display_name":"Siva Theja Maguluri","orcid":"https://orcid.org/0000-0002-5797-1639"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siva Theja Maguluri","raw_affiliation_strings":["School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5797-1639","affiliations":[{"raw_affiliation_string":"School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.9233,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.72011251,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"6","issue":null,"first_page":"2611","last_page":"2616"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.9937000274658203,"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/notation","display_name":"Notation","score":0.6366229057312012},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5481534004211426},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5392895936965942},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5226195454597473},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4366159439086914},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.404264897108078},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.34845373034477234},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.11893275380134583}],"concepts":[{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.6366229057312012},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5481534004211426},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5392895936965942},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5226195454597473},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4366159439086914},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.404264897108078},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.34845373034477234},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.11893275380134583},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lcsys.2022.3172242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2022.3172242","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"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 Control Systems Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G197761821","display_name":null,"funder_award_id":"CIF-1944993","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5986150752","display_name":"AI Institute for Advances in Optimization","funder_award_id":"2112533","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":110,"referenced_works":["https://openalex.org/W359568995","https://openalex.org/W594357522","https://openalex.org/W1547925194","https://openalex.org/W1575327902","https://openalex.org/W1646707810","https://openalex.org/W2019172585","https://openalex.org/W2046859786","https://openalex.org/W2047364871","https://openalex.org/W2071983464","https://openalex.org/W2074680702","https://openalex.org/W2075268401","https://openalex.org/W2082261506","https://openalex.org/W2091565802","https://openalex.org/W2094387729","https://openalex.org/W2099196192","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2124477018","https://openalex.org/W2130801532","https://openalex.org/W2139418546","https://openalex.org/W2147750403","https://openalex.org/W2151661095","https://openalex.org/W2155027007","https://openalex.org/W2156347136","https://openalex.org/W2156737235","https://openalex.org/W2162831327","https://openalex.org/W2165131254","https://openalex.org/W2165150801","https://openalex.org/W2172968643","https://openalex.org/W2173248099","https://openalex.org/W2251007294","https://openalex.org/W2400458653","https://openalex.org/W2575705757","https://openalex.org/W2594103415","https://openalex.org/W2766447205","https://openalex.org/W2788366696","https://openalex.org/W2885549115","https://openalex.org/W2904730732","https://openalex.org/W2914920107","https://openalex.org/W2946280430","https://openalex.org/W2953303875","https://openalex.org/W2953334758","https://openalex.org/W2962901215","https://openalex.org/W2963095800","https://openalex.org/W2963490519","https://openalex.org/W2963674921","https://openalex.org/W2963744705","https://openalex.org/W2963882293","https://openalex.org/W2963923407","https://openalex.org/W2963946945","https://openalex.org/W2963985863","https://openalex.org/W2964123095","https://openalex.org/W2964543613","https://openalex.org/W2966363432","https://openalex.org/W2970400802","https://openalex.org/W2971587637","https://openalex.org/W2981237928","https://openalex.org/W2995041734","https://openalex.org/W2998050631","https://openalex.org/W3011080757","https://openalex.org/W3021175792","https://openalex.org/W3022566517","https://openalex.org/W3023564296","https://openalex.org/W3034426742","https://openalex.org/W3035361730","https://openalex.org/W3035527463","https://openalex.org/W3038797447","https://openalex.org/W3038915804","https://openalex.org/W3039845099","https://openalex.org/W3041970508","https://openalex.org/W3044451384","https://openalex.org/W3046298552","https://openalex.org/W3101396171","https://openalex.org/W3103047293","https://openalex.org/W3103182070","https://openalex.org/W3104164965","https://openalex.org/W3117137507","https://openalex.org/W3124786193","https://openalex.org/W3127686539","https://openalex.org/W3127825666","https://openalex.org/W3129308573","https://openalex.org/W3129673291","https://openalex.org/W3131821770","https://openalex.org/W3136903997","https://openalex.org/W3159422316","https://openalex.org/W3160923286","https://openalex.org/W3164660575","https://openalex.org/W3167990336","https://openalex.org/W3171210634","https://openalex.org/W4214717370","https://openalex.org/W4288602110","https://openalex.org/W4318718437","https://openalex.org/W6632901617","https://openalex.org/W6679257226","https://openalex.org/W6683001934","https://openalex.org/W6683195989","https://openalex.org/W6683204974","https://openalex.org/W6748769517","https://openalex.org/W6758937863","https://openalex.org/W6767941141","https://openalex.org/W6769467134","https://openalex.org/W6777944346","https://openalex.org/W6779651760","https://openalex.org/W6780486084","https://openalex.org/W6789634427","https://openalex.org/W6789785855","https://openalex.org/W6790690321","https://openalex.org/W6791107212","https://openalex.org/W6795071623","https://openalex.org/W6795363010"],"related_works":["https://openalex.org/W2504004674","https://openalex.org/W2963177394","https://openalex.org/W1595229445","https://openalex.org/W2498744856","https://openalex.org/W4390482104","https://openalex.org/W322408318","https://openalex.org/W149041114","https://openalex.org/W1965815883","https://openalex.org/W763418848","https://openalex.org/W4298135613"],"abstract_inverted_index":{"In":[0,44],"this":[1,93],"letter,":[2],"we":[3,61,101,146],"develop":[4,62,102],"a":[5,21,63,77,103,180],"novel":[6],"variant":[7,104],"of":[8,24,41,97,105,117,140],"natural":[9,106],"actor-critic":[10],"algorithm":[11,75],"using":[12],"off-policy":[13,55],"sampling":[14],"and":[15,19,143],"linear":[16],"function":[17,59,110],"approximation,":[18,60,111],"establish":[20],"sample":[22,138,158],"complexity":[23],"<inline-formula":[25,67,80,118,127,150],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[26,68,81,119,128,151],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[27,69,82,120,129,152],"<tex-math":[28,70,83,121,130,153],"notation=\"LaTeX\">$\\mathcal":[29,122,154],"{O}{(}\\epsilon":[30,155],"^{-3}{)}$":[31,156],"</tex-math></inline-formula>":[32,72,85,125,133,157],",":[33],"outperforming":[34],"all":[35],"the":[36,48,136,141,144,167,170,175,186],"previously":[37],"known":[38],"convergence":[39,90,115],"bounds":[40,91,139],"such":[42],"algorithms.":[43],"order":[45],"to":[46,51,185],"overcome":[47],"divergence":[49],"due":[50],"deadly":[52],"triad":[53],"in":[54],"policy":[56,107,172],"evaluation":[57],"under":[58,109],"critic":[64],"that":[65,169],"employs":[66],"notation=\"LaTeX\">$n$":[71,84],"-step":[73],"TD-learning":[74],"with":[76,112],"properly":[78],"chosen":[79],".":[86],"We":[87],"present":[88],"finite-sample":[89],"on":[92,166],"critic,":[94,145],"which":[95,178],"are":[96],"independent":[98],"interest.":[99],"Furthermore,":[100],"gradient":[108],"an":[113,148],"improved":[114],"rate":[116],"{O}(1/\\mathsf":[123],"{T})$":[124],"after":[126],"notation=\"LaTeX\">$\\mathsf":[131],"{T}$":[132],"iterations.":[134],"Combining":[135],"finite":[137],"actor":[142],"obtain":[147],"overall":[149],"complexity.":[159],"Our":[160],"results":[161],"were":[162],"derived":[163],"solely":[164],"based":[165],"assumption":[168,183],"behavior":[171],"sufficiently":[173],"explores":[174],"state-action":[176],"space,":[177],"is":[179],"much":[181],"lighter":[182],"compared":[184],"related":[187],"literature.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}