{"id":"https://openalex.org/W4400555262","doi":"https://doi.org/10.1561/2400000045","title":"Stochastic Optimization Methods for Policy Evaluation in Reinforcement Learning","display_name":"Stochastic Optimization Methods for Policy Evaluation in Reinforcement Learning","publication_year":2024,"publication_date":"2024-07-11","ids":{"openalex":"https://openalex.org/W4400555262","doi":"https://doi.org/10.1561/2400000045"},"language":"en","primary_location":{"id":"doi:10.1561/2400000045","is_oa":false,"landing_page_url":"https://doi.org/10.1561/2400000045","pdf_url":null,"source":{"id":"https://openalex.org/S4210187074","display_name":"Foundations and Trends\u00ae in Optimization","issn_l":"2167-3888","issn":["2167-3888","2167-3918"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318575","host_organization_name":"Now Publishers","host_organization_lineage":["https://openalex.org/P4310318575"],"host_organization_lineage_names":["Now Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Foundations and Trends\u00ae in 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/A5101854122","display_name":"Yi Zhou","orcid":"https://orcid.org/0000-0003-2610-1523"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Zhou","raw_affiliation_strings":["University of Utah"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002089057","display_name":"Shaocong Ma","orcid":"https://orcid.org/0009-0007-4414-0303"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shacong Ma","raw_affiliation_strings":["University of Utah"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I223532165"],"apc_list":null,"apc_paid":null,"fwci":1.3024,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.84268164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"6","issue":"3","first_page":"145","last_page":"192"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.3224000036716461,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.3224000036716461,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.757419228553772},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6106480360031128},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5461814999580383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37510785460472107},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35892385244369507},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1938328742980957},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1633128523826599},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.08895590901374817}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.757419228553772},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6106480360031128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5461814999580383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37510785460472107},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35892385244369507},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1938328742980957},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1633128523826599},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08895590901374817}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1561/2400000045","is_oa":false,"landing_page_url":"https://doi.org/10.1561/2400000045","pdf_url":null,"source":{"id":"https://openalex.org/S4210187074","display_name":"Foundations and Trends\u00ae in Optimization","issn_l":"2167-3888","issn":["2167-3888","2167-3918"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318575","host_organization_name":"Now Publishers","host_organization_lineage":["https://openalex.org/P4310318575"],"host_organization_lineage_names":["Now Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Foundations and Trends\u00ae in Optimization","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":8,"referenced_works":["https://openalex.org/W1568229137","https://openalex.org/W1575327902","https://openalex.org/W1986446408","https://openalex.org/W2100677568","https://openalex.org/W2139418546","https://openalex.org/W2334782222","https://openalex.org/W2770898551","https://openalex.org/W4206742934"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588"],"abstract_inverted_index":{"This":[0,134],"monograph":[1,107,135],"introduces":[2,108],"various":[3],"value-based":[4],"approaches":[5],"for":[6],"solving":[7],"the":[8,13,23,56,59,67,124,131],"policy":[9,30,60,69],"evaluation":[10,57],"problem":[11],"in":[12,46,91],"online":[14],"reinforcement":[15],"learning":[16],"(RL)":[17],"scenario,":[18],"which":[19],"aims":[20],"to":[21,122],"learn":[22],"value":[24],"function":[25,84],"associated":[26],"with":[27,83],"a":[28,32,102],"specific":[29],"under":[31,101],"single":[33],"Markov":[34],"decision":[35],"process":[36],"(MDP).":[37],"Approaches":[38],"vary":[39],"depending":[40],"on":[41],"whether":[42],"they":[43],"are":[44,89,99,120],"implemented":[45],"an":[47],"on-policy":[48,53],"or":[49,86],"off-policy":[50,95],"manner:":[51],"In":[52],"settings,":[54],"where":[55,97],"of":[58],"is":[61,71],"conducted":[62],"using":[63],"data":[64],"generated":[65],"from":[66],"same":[68],"that":[70],"being":[72],"assessed,":[73],"classical":[74],"techniques":[75],"such":[76],"as":[77,130],"TD(0),":[78],"TD(\u03bb),":[79],"and":[80,115,143],"their":[81,138],"extensions":[82],"approximation":[85],"variance":[87],"reduction":[88],"employed":[90],"this":[92,106],"setting.":[93],"For":[94],"evaluation,":[96],"samples":[98],"collected":[100],"different":[103],"behavior":[104],"policy,":[105],"gradient-based":[109],"two-timescale":[110],"algorithms":[111,119],"like":[112],"GTD2,":[113],"TDC,":[114],"variance-reduced":[116],"TDC.":[117],"These":[118],"designed":[121],"minimize":[123],"mean-squared":[125],"projected":[126],"Bellman":[127],"error":[128],"(MSPBE)":[129],"objective":[132],"function.":[133],"also":[136],"discusses":[137],"finite-sample":[139],"convergence":[140],"upper":[141],"bounds":[142],"sample":[144],"complexity.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}