{"id":"https://openalex.org/W3194910469","doi":"https://doi.org/10.1137/21m144640x","title":"Robust Risk-Aware Reinforcement Learning","display_name":"Robust Risk-Aware Reinforcement Learning","publication_year":2022,"publication_date":"2022-03-01","ids":{"openalex":"https://openalex.org/W3194910469","doi":"https://doi.org/10.1137/21m144640x","mag":"3194910469"},"language":"en","primary_location":{"id":"doi:10.1137/21m144640x","doi":"https://doi.org/10.1137/21m144640x","is_oa":false,"landing_page_url":"https://doi.org/10.1137/21m144640x","pdf_url":null,"source":{"id":"https://openalex.org/S75627377","display_name":"SIAM Journal on Financial Mathematics","issn_l":"1945-497X","issn":["1945-497X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["abdc-b","anvur-class-a","anvur-scientific","cwts-core","dongbi-b","fnege-4","jufo-1","norway-2","poland-100","russia-white-list-2","vabb-shw"],"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 Financial Mathematics","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.2139/ssrn.3910498","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016897782","display_name":"Sebastian Jaimungal A","orcid":"https://orcid.org/0000-0002-0193-0993","observed_orcids":["https://orcid.org/0000-0002-0193-0993"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sebastian Jaimungal","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0193-0993","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005873558","display_name":"Silvana M. Pesenti","orcid":"https://orcid.org/0000-0002-6661-6970","observed_orcids":["https://orcid.org/0000-0002-6661-6970"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Silvana M. Pesenti","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6661-6970","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066330751","display_name":"Ye Sheng Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye Sheng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018777944","display_name":"Hariom Tatsat","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hariom Tatsat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0997,"has_fulltext":true,"cited_by_count":38,"citation_normalized_percentile":{"value":0.94424918,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":92,"max":99},"biblio":{"volume":"13","issue":"1","first_page":"213","last_page":"226"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11413","display_name":"Risk and Portfolio Optimization","score":0.9721999764442444,"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":0.9721999764442444,"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":0.00860000029206276,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0066999997943639755,"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/robust-reinforcement-learning","display_name":"robust reinforcement learning","score":0.8270000219345093},{"id":"https://openalex.org/keywords/risk-aware-optimization","display_name":"risk-aware optimization","score":0.7120000123977661},{"id":"https://openalex.org/keywords/rank-dependent-expected-utility","display_name":"rank-dependent utility","score":0.9769999980926514},{"id":"https://openalex.org/keywords/wasserstein-ambiguity-set","display_name":"Wasserstein ambiguity set","score":0.7369999885559082},{"id":"https://openalex.org/keywords/model-uncertainty","display_name":"model uncertainty","score":0.8880000114440918},{"id":"https://openalex.org/keywords/worst-case-distribution","display_name":"worst-case distribution","score":0.6600000262260437},{"id":"https://openalex.org/keywords/policy-gradient","display_name":"policy gradient","score":0.718999981880188},{"id":"https://openalex.org/keywords/benchmark-tracking","display_name":"benchmark tracking","score":0.6660000085830688},{"id":"https://openalex.org/keywords/statistical-arbitrage","display_name":"statistical arbitrage","score":0.8880000114440918},{"id":"https://openalex.org/keywords/risk-return-trade-off","display_name":"risk-return tradeoff","score":0.5920000076293945}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9045664072036743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6095670461654663},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5606092810630798},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.5382418632507324},{"id":"https://openalex.org/C160623529","wikidata":"https://www.wikidata.org/wiki/Q273088","display_name":"Arbitrage","level":2,"score":0.5093966126441956},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4835740923881531},{"id":"https://openalex.org/C2776719154","wikidata":"https://www.wikidata.org/wiki/Q1094965","display_name":"Downside risk","level":3,"score":0.4757135510444641},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46190980076789856},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.4365873336791992},{"id":"https://openalex.org/C193254401","wikidata":"https://www.wikidata.org/wiki/Q2160088","display_name":"Robust optimization","level":2,"score":0.4211937487125397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3026498854160309},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.23085731267929077},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18950042128562927},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11591756343841553},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.10070958733558655},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1137/21m144640x","doi":"https://doi.org/10.1137/21m144640x","is_oa":false,"landing_page_url":"https://doi.org/10.1137/21m144640x","pdf_url":null,"source":{"id":"https://openalex.org/S75627377","display_name":"SIAM Journal on Financial Mathematics","issn_l":"1945-497X","issn":["1945-497X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["abdc-b","anvur-class-a","anvur-scientific","cwts-core","dongbi-b","fnege-4","jufo-1","norway-2","poland-100","russia-white-list-2","vabb-shw"],"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 Financial Mathematics","raw_type":"journal-article"},{"id":"doi:10.2139/ssrn.3910498","doi":"https://doi.org/10.2139/ssrn.3910498","is_oa":true,"landing_page_url":"https://doi.org/10.2139/ssrn.3910498","pdf_url":null,"source":{"id":"https://openalex.org/S4210172589","display_name":"SSRN Electronic Journal","issn_l":"1556-5068","issn":["1556-5068"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1318003438","host_organization_name":"RELX Group (Netherlands)","host_organization_lineage":["https://openalex.org/I1318003438"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"pmh:oai:RePEc:arx:papers:2108.10403","doi":null,"is_oa":false,"landing_page_url":"http://arxiv.org/pdf/2108.10403","pdf_url":"http://arxiv.org/pdf/2108.10403","source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"preprint"},{"id":"pmh:oai:arXiv.org:2108.10403","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.10403","pdf_url":"https://arxiv.org/pdf/2108.10403","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3194910469","doi":null,"is_oa":false,"landing_page_url":"https://EconPapers.repec.org/RePEc:arx:papers:2108.10403","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"RePEc: Research Papers in Economics","raw_type":null},{"id":"doi:10.48550/arxiv.2108.10403","doi":"https://doi.org/10.48550/arxiv.2108.10403","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2108.10403","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.2139/ssrn.3910498","doi":"https://doi.org/10.2139/ssrn.3910498","is_oa":true,"landing_page_url":"https://doi.org/10.2139/ssrn.3910498","pdf_url":null,"source":{"id":"https://openalex.org/S4210172589","display_name":"SSRN Electronic Journal","issn_l":"1556-5068","issn":["1556-5068"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1318003438","host_organization_name":"RELX Group (Netherlands)","host_organization_lineage":["https://openalex.org/I1318003438"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1283901253","display_name":null,"funder_award_id":"04289","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G1359752570","display_name":"Stochastic Control and Games in Intraday Markets","funder_award_id":"rgpin-2018-05705","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G2271590008","display_name":null,"funder_award_id":"RGPIN 2020","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G6545586602","display_name":"Sensitivity, uncertainty and robustness of risk models in insurance","funder_award_id":"dgecr-2020-00333","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G6981648434","display_name":"Sensitivity, uncertainty and robustness of risk models in insurance","funder_award_id":"rgpin-2020-04289","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G761669796","display_name":null,"funder_award_id":"RGPAS-2018-522715","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G814497173","display_name":null,"funder_award_id":"RGPIN 2018","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3194910469.pdf","grobid_xml":"https://content.openalex.org/works/W3194910469.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W646582900","https://openalex.org/W1585575029","https://openalex.org/W1712265143","https://openalex.org/W2056819186","https://openalex.org/W2101075098","https://openalex.org/W2129462326","https://openalex.org/W2166292404","https://openalex.org/W2170923204","https://openalex.org/W2473797792","https://openalex.org/W2778939515","https://openalex.org/W2917175941","https://openalex.org/W2966684444","https://openalex.org/W3087158902","https://openalex.org/W3090308802","https://openalex.org/W3097026541","https://openalex.org/W3100532071","https://openalex.org/W3110347183","https://openalex.org/W3125653313","https://openalex.org/W3128776309","https://openalex.org/W3135191218","https://openalex.org/W3191777097","https://openalex.org/W4385386470","https://openalex.org/W4388296094"],"related_works":["https://openalex.org/W7125692729","https://openalex.org/W4288079541","https://openalex.org/W4285403797","https://openalex.org/W4225482307","https://openalex.org/W4294690570","https://openalex.org/W3028683606","https://openalex.org/W3036684478","https://openalex.org/W4226261790","https://openalex.org/W7118012772","https://openalex.org/W2104402102"],"abstract_inverted_index":{"We":[0,112],"present":[1],"a":[2,19,30,60,76,92],"reinforcement":[3],"learning":[4],"(RL)":[5],"approach":[6],"for":[7,118],"robust":[8,133],"optimization":[9],"of":[10,22,29,106],"risk-aware":[11],"performance":[12,105],"criteria.":[13],"To":[14,51],"allow":[15],"agents":[16,40],"to":[17,41,102],"express":[18],"wide":[20],"variety":[21],"risk-reward":[23],"profiles,":[24],"we":[25,58],"assess":[26,59],"the":[27,69,98,104,119],"value":[28],"policy":[31,61,93,115],"using":[32],"rank":[33],"dependent":[34],"expected":[35],"utility":[36],"(RDEU).":[37],"RDEU":[38],"allows":[39],"seek":[42],"gains,":[43],"while":[44],"simultaneously":[45],"protecting":[46],"themselves":[47],"against":[48,55],"downside":[49],"risk.":[50],"robustify":[52],"optimal":[53],"policies":[54],"model":[56],"uncertainty,":[57],"not":[62],"by":[63,68],"its":[64],"distribution":[65,72],"but":[66],"rather":[67],"worst":[70],"possible":[71],"that":[73,107],"lies":[74],"within":[75],"Wasserstein":[77],"ball":[78],"around":[79],"it.":[80],"Thus,":[81],"our":[82],"problem":[83],"formulation":[84],"may":[85],"be":[86],"viewed":[87],"as":[88],"an":[89],"actor/agent":[90],"choosing":[91],"(the":[94,109],"outer":[95,122],"problem)":[96],"and":[97,121,124,138],"adversary":[99],"then":[100],"acting":[101],"worsen":[103],"strategy":[108],"inner":[110,120],"problem).":[111],"develop":[113],"explicit":[114],"gradient":[116],"formulae":[117],"problems":[123],"show":[125],"their":[126],"efficacy":[127],"on":[128],"three":[129],"prototypical":[130],"financial":[131],"problems:":[132],"portfolio":[134],"allocation,":[135],"benchmark":[136],"optimization,":[137],"statistical":[139],"arbitrage.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2021-08-30T00:00:00"}
