{"id":"https://openalex.org/W4381739798","doi":"https://doi.org/10.1137/21m1456789","title":"Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence","display_name":"Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence","publication_year":2023,"publication_date":"2023-06-22","ids":{"openalex":"https://openalex.org/W4381739798","doi":"https://doi.org/10.1137/21m1456789"},"language":"en","primary_location":{"id":"doi:10.1137/21m1456789","is_oa":false,"landing_page_url":"https://doi.org/10.1137/21m1456789","pdf_url":null,"source":{"id":"https://openalex.org/S928796702","display_name":"SIAM Journal on Optimization","issn_l":"1052-6234","issn":["1052-6234","1095-7189"],"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 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/A5072190520","display_name":"Wenhao Zhan","orcid":"https://orcid.org/0000-0003-2529-5872"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenhao Zhan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ 08544 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ 08544 USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091389636","display_name":"Shicong Cen","orcid":null},"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":"Shicong Cen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213 USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032533257","display_name":"Baihe Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baihe Huang","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, Berkeley, CA 94720 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, Berkeley, CA 94720 USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100416078","display_name":"Yuxin Chen","orcid":"https://orcid.org/0000-0001-9256-5815"},"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":"Yuxin Chen","raw_affiliation_strings":["Department of Statistics and Data Science, Wharton School, University of Pennsylvania, Philadelphia, PA 19104 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Data Science, Wharton School, University of Pennsylvania, Philadelphia, PA 19104 USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059740024","display_name":"Jason D. Lee","orcid":"https://orcid.org/0000-0003-0064-7800"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason D. Lee","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ 08544 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ 08544 USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","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 15213 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 15213 USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9369,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.92651858,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"33","issue":"2","first_page":"1061","last_page":"1091"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9958000183105469,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9894000291824341,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.733259379863739},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6258187294006348},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6116465926170349},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5575234889984131},{"id":"https://openalex.org/keywords/convex-function","display_name":"Convex function","score":0.5039450526237488},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.47850027680397034},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.463399201631546},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.45742595195770264},{"id":"https://openalex.org/keywords/convexity","display_name":"Convexity","score":0.45674389600753784},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4510473906993866},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4469680190086365},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.4397600293159485},{"id":"https://openalex.org/keywords/bregman-divergence","display_name":"Bregman divergence","score":0.4264722764492035},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.33613717555999756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23817694187164307},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2371366024017334},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.18080338835716248}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.733259379863739},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6258187294006348},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6116465926170349},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5575234889984131},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.5039450526237488},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.47850027680397034},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.463399201631546},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.45742595195770264},{"id":"https://openalex.org/C72134830","wikidata":"https://www.wikidata.org/wiki/Q5166524","display_name":"Convexity","level":2,"score":0.45674389600753784},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4510473906993866},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4469680190086365},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.4397600293159485},{"id":"https://openalex.org/C149073432","wikidata":"https://www.wikidata.org/wiki/Q4960382","display_name":"Bregman divergence","level":2,"score":0.4264722764492035},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.33613717555999756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23817694187164307},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2371366024017334},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.18080338835716248},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/21m1456789","is_oa":false,"landing_page_url":"https://doi.org/10.1137/21m1456789","pdf_url":null,"source":{"id":"https://openalex.org/S928796702","display_name":"SIAM Journal on Optimization","issn_l":"1052-6234","issn":["1052-6234","1095-7189"],"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 Optimization","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1056225131","display_name":null,"funder_award_id":"FA9550-22-1-0198","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"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"},{"id":"https://openalex.org/G1580069250","display_name":null,"funder_award_id":"CCF-1901199","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1724375350","display_name":null,"funder_award_id":"IIS-2218713","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2376053866","display_name":null,"funder_award_id":"N00014-22-1-2354","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G2842829996","display_name":null,"funder_award_id":"CNS-2148212","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2955375631","display_name":null,"funder_award_id":"W911NF-11-1-0304","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G3582032785","display_name":null,"funder_award_id":"CCF-2007911","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3758565161","display_name":null,"funder_award_id":"IIS 2107304","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4074345793","display_name":null,"funder_award_id":"CCF-2221009","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5741479072","display_name":null,"funder_award_id":"DMS-2134080","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5945795592","display_name":null,"funder_award_id":"CCF-1907661","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6758875932","display_name":null,"funder_award_id":"CCF 2002272","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6938454608","display_name":null,"funder_award_id":"CCF-2106778","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7580596982","display_name":null,"funder_award_id":"IIS-2218773","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"},{"id":"https://openalex.org/F4320306151","display_name":"Alfred P. Sloan Foundation","ror":"https://ror.org/052csg198"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320310207","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1983874169","https://openalex.org/W1993411524","https://openalex.org/W2016384870","https://openalex.org/W2042860556","https://openalex.org/W2067272684","https://openalex.org/W2098432798","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2963576857","https://openalex.org/W2964037929","https://openalex.org/W3127686539","https://openalex.org/W3209135762","https://openalex.org/W3217314940","https://openalex.org/W4298023569"],"related_works":["https://openalex.org/W2765284782","https://openalex.org/W2152670157","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2903299703","https://openalex.org/W2156021013","https://openalex.org/W2016648086","https://openalex.org/W3105579180","https://openalex.org/W4399157305"],"abstract_inverted_index":{".Policy":[0],"optimization,":[1],"which":[2,74],"learns":[3],"the":[4,10,19,39,52,76,123,145,157,173,190,206],"policy":[5,54,99,112,194,198],"of":[6,21,41,46,51,111,130,139,144,164,192,211],"interest":[7],"by":[8,69],"maximizing":[9],"value":[11,29,78],"function":[12,79],"via":[13],"large-scale":[14],"optimization":[15],"techniques,":[16],"lies":[17],"at":[18],"heart":[20],"modern":[22],"reinforcement":[23],"learning":[24,165],"(RL).":[25],"In":[26,180],"addition":[27],"to":[28,56,71,156,204],"maximization,":[30],"other":[31],"practical":[32],"considerations":[33,63],"arise":[34],"commonly":[35],"as":[36,133,135],"well,":[37],"including":[38],"need":[40],"encouraging":[42],"exploration,":[43],"and":[44,59,178,196,208],"that":[45,151],"ensuring":[47],"certain":[48],"structural":[49],"properties":[50],"learned":[53],"due":[55],"safety,":[57],"resource,":[58],"operational":[60],"constraints.":[61],"These":[62],"can":[64],"often":[65],"be":[66],"accounted":[67],"for":[68,104],"resorting":[70],"regularized":[72,106],"RL,":[73],"augments":[75],"target":[77],"with":[80],"a":[81,97,109,127,136,168],"structure-promoting":[82],"regularization":[83],"term.":[84],"Focusing":[85],"on":[86],"an":[87,161],"infinite-horizon":[88],"discounted":[89],"tabular":[90],"Markov":[91],"decision":[92],"process,":[93],"this":[94,182],"paper":[95],"proposes":[96],"generalized":[98],"mirror":[100,113,213],"descent":[101,114],"(GPMD)":[102],"algorithm":[103,125,153],"solving":[105],"RL.":[107],"As":[108],"generalization":[110],"[G.":[115],"Lan,":[116],"Math.":[117],"Program.,":[118],"198":[119],"(2023),":[120],"pp.":[121],"1059\u20131106],":[122],"proposed":[124],"accommodates":[126],"general":[128],"class":[129],"convex":[131],"regularizers":[132],"well":[134],"broad":[137],"family":[138],"Bregman":[140],"divergence":[141],"in":[142,147,167,189],"cognizance":[143],"regularizer":[146,174],"use.":[148],"We":[149],"demonstrate":[150],"our":[152],"converges":[154],"linearly":[155],"global":[158],"solution":[159],"over":[160],"entire":[162],"range":[163],"rates,":[166],"dimension-free":[169],"fashion,":[170],"even":[171],"when":[172],"lacks":[175],"strong":[176],"convexity":[177],"smoothness.":[179],"addition,":[181],"linear":[183],"convergence":[184],"feature":[185],"is":[186],"provably":[187],"stable":[188],"face":[191],"inexact":[193],"evaluation":[195],"imperfect":[197],"updates.":[199],"Numerical":[200],"experiments":[201],"are":[202],"provided":[203],"corroborate":[205],"applicability":[207],"appealing":[209],"performance":[210],"GPMD.Keywordspolicy":[212],"descentBregman":[214],"divergenceregularizationpolicy":[215],"optimizationMSC":[216],"codes68Q2568Q3290C26":[217]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}