{"id":"https://openalex.org/W4402916911","doi":"https://doi.org/10.1109/tac.2024.3469328","title":"A Simple Finite-Time Analysis of TD Learning With Linear Function Approximation","display_name":"A Simple Finite-Time Analysis of TD Learning With Linear Function Approximation","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402916911","doi":"https://doi.org/10.1109/tac.2024.3469328"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2024.3469328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2024.3469328","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/A5106470034","display_name":"A. Mitra","orcid":"https://orcid.org/0009-0004-4590-553X"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aritra Mitra","raw_affiliation_strings":["Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USA","Department of Electrical and Computer Engineering, North Carolina State University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, North Carolina State University, USA","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5106470034"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":1.0425,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.81156152,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"70","issue":"2","first_page":"1388","last_page":"1394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9327999949455261,"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/T10320","display_name":"Neural Networks and Applications","score":0.9327999949455261,"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/simple","display_name":"Simple (philosophy)","score":0.6913203001022339},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4865633547306061},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.48598894476890564},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4679974913597107},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4670599400997162},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.4283868372440338},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.4151991605758667},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4021334648132324},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37889012694358826},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.336607426404953},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.23741444945335388},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1841762661933899},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14821085333824158},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.08430621027946472}],"concepts":[{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6913203001022339},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4865633547306061},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.48598894476890564},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4679974913597107},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4670599400997162},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4283868372440338},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.4151991605758667},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4021334648132324},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37889012694358826},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.336607426404953},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.23741444945335388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1841762661933899},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14821085333824158},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.08430621027946472},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2024.3469328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2024.3469328","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1999254175","https://openalex.org/W2077343054","https://openalex.org/W2139418546","https://openalex.org/W2885549115","https://openalex.org/W2963616027","https://openalex.org/W2964123095","https://openalex.org/W3041202696","https://openalex.org/W4380669412","https://openalex.org/W4391020374","https://openalex.org/W6639835816","https://openalex.org/W6703110798","https://openalex.org/W6744304049","https://openalex.org/W6752979356","https://openalex.org/W6758937863","https://openalex.org/W6767353287","https://openalex.org/W6773637655","https://openalex.org/W6782879080","https://openalex.org/W6803418194","https://openalex.org/W6848766311","https://openalex.org/W6859625924","https://openalex.org/W6861650126"],"related_works":["https://openalex.org/W1585007175","https://openalex.org/W2382521049","https://openalex.org/W2144385241","https://openalex.org/W4300101996","https://openalex.org/W2165950148","https://openalex.org/W4253593777","https://openalex.org/W2951497643","https://openalex.org/W2142393343","https://openalex.org/W2338854850","https://openalex.org/W2184239527"],"abstract_inverted_index":{"We":[0,45,166],"study":[1],"the":[2,27,31,43,54,67,84,105,117,126,138,148,177],"finite-time":[3],"convergence":[4],"of":[5,42,56,97,129,140,150,179,191],"temporal-difference":[6],"(TD)":[7],"learning":[8,110,131],"with":[9],"linear":[10],"function":[11],"approximation":[12,183],"under":[13,93],"Markovian":[14,151],"sampling.":[15,152],"Existing":[16],"proofs":[17],"for":[18],"this":[19,75],"setting":[20],"either":[21],"assume":[22],"a":[23,35,57,63,79,94,98,122,134],"projection":[24,64],"step":[25,65],"in":[26,66,114,176],"algorithm":[28],"to":[29,39,52,73,90,133,157],"simplify":[30],"analysis,":[32],"or":[33],"require":[34],"fairly":[36],"intricate":[37],"argument":[38],"ensure":[40],"stability":[41],"iterates.":[44],"ask:":[46],"<italic":[47],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[48,102,142],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Is":[49],"it":[50],"possible":[51,77],"retain":[53],"simplicity":[55],"projection-based":[58],"analysis":[59],"without":[60],"actually":[61],"performing":[62],"algorithm?</i>":[68],"Our":[69],"main":[70],"contribution":[71],"is":[72,76],"show":[74],"via":[78],"novel":[80],"two-step":[81],"argument.":[82],"In":[83,116],"first":[85],"step,":[86,119],"we":[87,120],"use":[88],"induction":[89],"prove":[91],"that":[92,124,146,161,168],"standard":[95],"choice":[96],"constant":[99],"step-size":[100],"<inline-formula":[101,141],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[103,143],"notation=\"LaTeX\">$\\alpha$</tex-math></inline-formula>,":[104],"iterates":[106],"generated":[107],"by":[108,187],"TD":[109,130],"remain":[111],"uniformly":[112],"bounded":[113,135],"expectation.":[115],"second":[118],"establish":[121],"recursion":[123],"mimics":[125],"steady-state":[127],"dynamics":[128],"up":[132],"perturbation":[136],"on":[137],"order":[139],"notation=\"LaTeX\">$O(\\alpha":[144],"^{2})$</tex-math></inline-formula>":[145],"captures":[147],"effect":[149],"Combining":[153],"these":[154],"pieces":[155],"leads":[156],"an":[158],"overall":[159],"approach":[160],"considerably":[162],"simplifies":[163],"existing":[164],"proofs.":[165],"conjecture":[167],"our":[169],"inductive":[170],"proof":[171],"technique":[172],"will":[173],"find":[174],"applications":[175],"analyses":[178],"more":[180],"complex":[181],"stochastic":[182],"algorithms,":[184],"and":[185],"conclude":[186],"providing":[188],"some":[189],"examples":[190],"such":[192],"applications.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
