{"id":"https://openalex.org/W4317792448","doi":"https://doi.org/10.1109/wsc57314.2022.10015394","title":"Policy Evaluation with Stochastic Gradient Estimation Techniques","display_name":"Policy Evaluation with Stochastic Gradient Estimation Techniques","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4317792448","doi":"https://doi.org/10.1109/wsc57314.2022.10015394"},"language":"en","primary_location":{"id":"doi:10.1109/wsc57314.2022.10015394","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/wsc57314.2022.10015394","pdf_url":null,"source":{"id":"https://openalex.org/S4363607869","display_name":"2022 Winter Simulation Conference (WSC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 Winter Simulation Conference (WSC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5044769501","display_name":"Yi Zhou","orcid":"https://orcid.org/0000-0002-9023-4374"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Zhou","raw_affiliation_strings":["Institute for Systems Research, University of Maryland,Department of Mathematics,College Park,MD,USA,20742"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Systems Research, University of Maryland,Department of Mathematics,College Park,MD,USA,20742","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000889975","display_name":"Michael C. Fu","orcid":"https://orcid.org/0000-0003-2105-4932"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael C. Fu","raw_affiliation_strings":["Robert H. Smith School of Business, Institute for Systems Research, University of Maryland,College Park,MD,USA,20742"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robert H. Smith School of Business, Institute for Systems Research, University of Maryland,College Park,MD,USA,20742","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044367354","display_name":"Ilya O. Ryzhov","orcid":"https://orcid.org/0000-0002-4191-084X"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ilya O. Ryzhov","raw_affiliation_strings":["Robert H. Smith School of Business, University of Maryland,College Park,MD,USA,20742"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robert H. Smith School of Business, University of Maryland,College Park,MD,USA,20742","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"3039","last_page":"3050"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11413","display_name":"Risk and Portfolio Optimization","score":0.9958000183105469,"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"}},"topics":[{"id":"https://openalex.org/T11413","display_name":"Risk and Portfolio Optimization","score":0.9958000183105469,"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"}},{"id":"https://openalex.org/T10067","display_name":"Stochastic processes and financial applications","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.7606292963027954},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5537958741188049},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.5315349698066711},{"id":"https://openalex.org/keywords/conditional-expectation","display_name":"Conditional expectation","score":0.5257179141044617},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5198731422424316},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5070993900299072},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4786494970321655},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.47549188137054443},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.46113312244415283},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4539808928966522},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.451036274433136},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4492208659648895},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.2358999252319336},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.20657622814178467},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17702323198318481},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.08026126027107239}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7606292963027954},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5537958741188049},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5315349698066711},{"id":"https://openalex.org/C186215838","wikidata":"https://www.wikidata.org/wiki/Q772232","display_name":"Conditional expectation","level":2,"score":0.5257179141044617},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5198731422424316},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5070993900299072},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4786494970321655},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.47549188137054443},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.46113312244415283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4539808928966522},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.451036274433136},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4492208659648895},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2358999252319336},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.20657622814178467},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17702323198318481},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.08026126027107239},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wsc57314.2022.10015394","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/wsc57314.2022.10015394","pdf_url":null,"source":{"id":"https://openalex.org/S4363607869","display_name":"2022 Winter Simulation Conference (WSC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 Winter Simulation Conference (WSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3747973309","display_name":null,"funder_award_id":"FA95502010211","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1499021337","https://openalex.org/W1593494339","https://openalex.org/W1987308858","https://openalex.org/W1988288472","https://openalex.org/W2006036383","https://openalex.org/W2126311658","https://openalex.org/W2139418546","https://openalex.org/W2492794003","https://openalex.org/W2787618032","https://openalex.org/W2922692025","https://openalex.org/W2963616027","https://openalex.org/W3041202696","https://openalex.org/W3132558922","https://openalex.org/W4212774754","https://openalex.org/W4213450758","https://openalex.org/W4214717370","https://openalex.org/W4233696721","https://openalex.org/W4306822038","https://openalex.org/W6676021584","https://openalex.org/W6683204974"],"related_works":["https://openalex.org/W4287880334","https://openalex.org/W4366700029","https://openalex.org/W4285230481","https://openalex.org/W4385769873","https://openalex.org/W2015759683","https://openalex.org/W4281634296","https://openalex.org/W4319161863","https://openalex.org/W2371687270","https://openalex.org/W4307819175","https://openalex.org/W4311888330"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,50],"consider":[4],"policy":[5,55],"evaluation":[6,56],"in":[7],"a":[8,23,32],"finite-horizon":[9],"setting":[10],"with":[11],"continuous":[12],"state":[13,65],"variables.":[14],"The":[15],"Bellman":[16],"equation":[17],"represents":[18],"the":[19,40,45,60],"value":[20,61],"function":[21],"as":[22],"conditional":[24],"expectation,":[25],"which":[26],"can":[27,66],"be":[28,67],"further":[29],"transformed":[30],"into":[31],"ratio":[33,48],"of":[34,62],"two":[35],"stochastic":[36],"gradients.":[37],"By":[38],"using":[39,69],"finite":[41],"difference":[42],"method":[43],"and":[44,57],"generalized":[46],"likelihood":[47],"method,":[49],"propose":[51],"new":[52],"estimators":[53],"for":[54],"show":[58],"how":[59],"any":[63],"given":[64],"estimated":[68],"sample":[70],"paths":[71],"starting":[72],"from":[73],"various":[74],"other":[75],"states.":[76]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}