{"id":"https://openalex.org/W4396215051","doi":"https://doi.org/10.1109/tit.2024.3394685","title":"High-Probability Sample Complexities for Policy Evaluation With Linear Function Approximation","display_name":"High-Probability Sample Complexities for Policy Evaluation With Linear Function Approximation","publication_year":2024,"publication_date":"2024-04-29","ids":{"openalex":"https://openalex.org/W4396215051","doi":"https://doi.org/10.1109/tit.2024.3394685"},"language":"en","primary_location":{"id":"doi:10.1109/tit.2024.3394685","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/tit.2024.3394685","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"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 Information Theory","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/A5100357040","display_name":"Gen Li","orcid":"https://orcid.org/0000-0002-7298-2141"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Gen Li","raw_affiliation_strings":["Department of Statistics, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072239003","display_name":"Weichen Wu","orcid":"https://orcid.org/0000-0002-5955-3289"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weichen Wu","raw_affiliation_strings":["Department of Statistics and Data Science, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5955-3289","affiliations":[{"raw_affiliation_string":"Department of Statistics and Data Science, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053809095","display_name":"Yuejie Chi","orcid":"https://orcid.org/0000-0002-6766-5459"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuejie Chi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6766-5459","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074490643","display_name":"Cong Ma","orcid":"https://orcid.org/0000-0003-2532-0038"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Ma","raw_affiliation_strings":["Department of Statistics, The University of Chicago, Chicago, IL, USA"],"raw_orcid":"https://orcid.org/0000-0003-2532-0038","affiliations":[{"raw_affiliation_string":"Department of Statistics, The University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112007828","display_name":"Alessandro Rinaldo","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alessandro Rinaldo","raw_affiliation_strings":["Department of Statistics and Data Science, The University of Texas at Austin, Austin, UT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Data Science, The University of Texas at Austin, Austin, UT, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005015806","display_name":"Yuting Wei","orcid":"https://orcid.org/0000-0003-1488-4647"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuting Wei","raw_affiliation_strings":["Department of Statistics and Data Science, The Wharton School, University of Pennsylvania, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1488-4647","affiliations":[{"raw_affiliation_string":"Department of Statistics and Data Science, The Wharton School, University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04388308,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"70","issue":"8","first_page":"5969","last_page":"5999"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9994000196456909,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.6782901287078857},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6479183435440063},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5996662378311157},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5944595336914062},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.5683723092079163},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5125477313995361},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5118014216423035},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5018196105957031},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.49365124106407166},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.440125435590744},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4063591957092285},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3865779936313629},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.17271730303764343}],"concepts":[{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.6782901287078857},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6479183435440063},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5996662378311157},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5944595336914062},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5683723092079163},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5125477313995361},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5118014216423035},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5018196105957031},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.49365124106407166},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.440125435590744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4063591957092285},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3865779936313629},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17271730303764343},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tit.2024.3394685","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/tit.2024.3394685","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"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 Information Theory","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1469985387","display_name":null,"funder_award_id":"N00014-19-1-2404","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1511694993","https://openalex.org/W1646707810","https://openalex.org/W1941445455","https://openalex.org/W1992208280","https://openalex.org/W1994616650","https://openalex.org/W2014944833","https://openalex.org/W2043382637","https://openalex.org/W2071983464","https://openalex.org/W2075268401","https://openalex.org/W2098432798","https://openalex.org/W2121703796","https://openalex.org/W2137798267","https://openalex.org/W2139418546","https://openalex.org/W2150147323","https://openalex.org/W2156779765","https://openalex.org/W2165612525","https://openalex.org/W2745868649","https://openalex.org/W2959895084","https://openalex.org/W2963616027","https://openalex.org/W2964019528","https://openalex.org/W2964123095","https://openalex.org/W2969337892","https://openalex.org/W2996964934","https://openalex.org/W3015956888","https://openalex.org/W3020075106","https://openalex.org/W3041202696","https://openalex.org/W3090442079","https://openalex.org/W3100124730","https://openalex.org/W3102674085","https://openalex.org/W3111378937","https://openalex.org/W3124408148","https://openalex.org/W3203759272","https://openalex.org/W3204262831","https://openalex.org/W3207876914","https://openalex.org/W4206039841","https://openalex.org/W4292973685","https://openalex.org/W4328051309","https://openalex.org/W4366692289","https://openalex.org/W4391410851","https://openalex.org/W4392591475","https://openalex.org/W4394842226","https://openalex.org/W6612245137","https://openalex.org/W6630907848","https://openalex.org/W6635767209","https://openalex.org/W6677984395","https://openalex.org/W6689664320","https://openalex.org/W6704084210","https://openalex.org/W6727147046","https://openalex.org/W6742958495","https://openalex.org/W6750027077","https://openalex.org/W6750582509","https://openalex.org/W6752725515","https://openalex.org/W6754906582","https://openalex.org/W6757677476","https://openalex.org/W6758937863","https://openalex.org/W6763800524","https://openalex.org/W6766156165","https://openalex.org/W6767047231","https://openalex.org/W6767092952","https://openalex.org/W6773140934","https://openalex.org/W6774823833","https://openalex.org/W6775323432","https://openalex.org/W6775935937","https://openalex.org/W6776530296","https://openalex.org/W6777944346","https://openalex.org/W6780426602","https://openalex.org/W6785813600","https://openalex.org/W6786754547","https://openalex.org/W6787043984","https://openalex.org/W6792120457","https://openalex.org/W6795051002","https://openalex.org/W6796019251","https://openalex.org/W6796971187","https://openalex.org/W6799359760","https://openalex.org/W6802394580","https://openalex.org/W6802441081","https://openalex.org/W6811051195"],"related_works":["https://openalex.org/W2016058626","https://openalex.org/W2474724840","https://openalex.org/W2963760573","https://openalex.org/W185788778","https://openalex.org/W1970303738","https://openalex.org/W4303635220","https://openalex.org/W2315999538","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"This":[0],"paper":[1],"is":[2],"concerned":[3],"with":[4,10,55,98],"the":[5,23,34,44,51,62,70,74,88,93,104,108,123,131,140,143,147],"problem":[6,137,148],"of":[7,33,142],"policy":[8,41,84],"evaluation":[9,42],"linear":[11,36,53],"function":[12],"approximation":[13],"in":[14,122],"discounted":[15],"infinite":[16],"horizon":[17],"Markov":[18],"decision":[19],"processes.":[20],"We":[21,111],"investigate":[22],"sample":[24,95],"complexities":[25],"required":[26],"to":[27],"guarantee":[28,101],"a":[29,82],"predefined":[30],"estimation":[31],"error":[32],"best":[35],"coefficients":[37],"for":[38],"two":[39],"widely-used":[40],"algorithms:":[43],"temporal":[45],"difference":[46],"(TD)":[47],"learning":[48],"algorithm":[49],"and":[50,73,120,146],"two-timescale":[52],"TD":[54],"gradient":[56],"correction":[57],"(TDC)":[58],"algorithm.":[59],"In":[60],"both":[61],"on-policy":[63,124],"setting,":[64,76],"where":[65,77],"observations":[66],"are":[67,79],"generated":[68],"from":[69,81,87],"target":[71,89],"policy,":[72,90],"off-policy":[75],"samples":[78],"drawn":[80],"behavior":[83],"potentially":[85],"different":[86],"we":[91],"establish":[92],"first":[94],"complexity":[96],"bound":[97,129,134],"high-probability":[99],"convergence":[100],"that":[102,126],"attains":[103],"optimal":[105],"dependence":[106,116],"on":[107,117,135],"tolerance":[109],"level.":[110],"also":[112],"exhibit":[113],"an":[114],"explicit":[115],"problem-related":[118],"quantities,":[119],"show":[121],"setting":[125],"our":[127],"upper":[128],"matches":[130],"minimax":[132],"lower":[133],"crucial":[136],"parameters,":[138],"including":[139],"choice":[141],"feature":[144],"map":[145],"dimension.":[149]},"counts_by_year":[],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}