{"id":"https://openalex.org/W4388659590","doi":"https://doi.org/10.1137/22m1527209","title":"Conditionally Elicitable Dynamic Risk Measures for Deep Reinforcement Learning","display_name":"Conditionally Elicitable Dynamic Risk Measures for Deep Reinforcement Learning","publication_year":2023,"publication_date":"2023-11-14","ids":{"openalex":"https://openalex.org/W4388659590","doi":"https://doi.org/10.1137/22m1527209"},"language":"en","primary_location":{"id":"doi:10.1137/22m1527209","is_oa":false,"landing_page_url":"https://doi.org/10.1137/22m1527209","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,"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"},"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/A5004743961","display_name":"Anthony Coache","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Anthony Coache","raw_affiliation_strings":["Department of Statistical Sciences, University of Toronto, Toronto, Ontario, M5G 1Z5, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistical Sciences, University of Toronto, Toronto, Ontario, M5G 1Z5, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016897782","display_name":"Sebastian Jaimungal","orcid":"https://orcid.org/0000-0002-0193-0993"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I9267121","display_name":"Fields Institute for Research in Mathematical Sciences","ror":"https://ror.org/03zzj3f20","country_code":"CA","type":"facility","lineage":["https://openalex.org/I185261750","https://openalex.org/I9267121"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sebastian Jaimungal","raw_affiliation_strings":["Department of Statistical Sciences, University of Toronto, Toronto, Ontario, M5G 1Z5, Canada; and Oxford-Man Institute of Quantitative Finance, Oxford, OX2 6ED, United Kingdom","Department of Statistical Sciences, University of Toronto, Toronto, Ontario, M5G 1Z5, Canada"],"raw_orcid":"https://orcid.org/0000-0002-0193-0993","affiliations":[{"raw_affiliation_string":"Department of Statistical Sciences, University of Toronto, Toronto, Ontario, M5G 1Z5, Canada; and Oxford-Man Institute of Quantitative Finance, Oxford, OX2 6ED, United Kingdom","institution_ids":["https://openalex.org/I9267121"]},{"raw_affiliation_string":"Department of Statistical Sciences, University of Toronto, Toronto, Ontario, M5G 1Z5, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040951539","display_name":"\u00c1lvaro Cartea","orcid":"https://orcid.org/0000-0002-7426-4645"},"institutions":[{"id":"https://openalex.org/I4210120676","display_name":"Mathematical Institute of the Slovak Academy of Sciences","ror":"https://ror.org/02fhy7464","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210120676"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"\u00c1lvaro Cartea","raw_affiliation_strings":["Oxford-Man Institute of Quantitative Finance & Mathematical Institute, University of Oxford, Oxford, OX2 9HB, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-7426-4645","affiliations":[{"raw_affiliation_string":"Oxford-Man Institute of Quantitative Finance & Mathematical Institute, University of Oxford, Oxford, OX2 9HB, United Kingdom","institution_ids":["https://openalex.org/I4210120676"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004743961"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":3.9449,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.9395167,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"14","issue":"4","first_page":"1249","last_page":"1289"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11413","display_name":"Risk and Portfolio Optimization","score":0.9988999962806702,"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":0.9988999962806702,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9965999722480774,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955999851226807,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.747250497341156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6393262147903442},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.536130964756012},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5232837796211243},{"id":"https://openalex.org/keywords/portfolio","display_name":"Portfolio","score":0.4831959009170532},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46276038885116577},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.446625292301178},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3846992552280426},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2098660171031952},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.10778611898422241},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.08862602710723877}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.747250497341156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6393262147903442},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.536130964756012},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5232837796211243},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.4831959009170532},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46276038885116577},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.446625292301178},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3846992552280426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2098660171031952},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.10778611898422241},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.08862602710723877}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/22m1527209","is_oa":false,"landing_page_url":"https://doi.org/10.1137/22m1527209","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,"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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1359752570","display_name":null,"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/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/G8474782591","display_name":null,"funder_award_id":"CGSD3-2019-534435","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334233","display_name":"Data Science Institute, Columbia University","ror":null},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1591570634","https://openalex.org/W1592048869","https://openalex.org/W1647779468","https://openalex.org/W1998274472","https://openalex.org/W2001009060","https://openalex.org/W2019291268","https://openalex.org/W2075965721","https://openalex.org/W2080787071","https://openalex.org/W2096643160","https://openalex.org/W2103496339","https://openalex.org/W2103590647","https://openalex.org/W2116421056","https://openalex.org/W2118940214","https://openalex.org/W2120465407","https://openalex.org/W2129462326","https://openalex.org/W2134866204","https://openalex.org/W2139786505","https://openalex.org/W2145339207","https://openalex.org/W2158581396","https://openalex.org/W2169206416","https://openalex.org/W2257979135","https://openalex.org/W2294586855","https://openalex.org/W2561666900","https://openalex.org/W2899507754","https://openalex.org/W2947626232","https://openalex.org/W3005377970","https://openalex.org/W3092690983","https://openalex.org/W3101267821","https://openalex.org/W3104441224","https://openalex.org/W3123498107","https://openalex.org/W3124098225","https://openalex.org/W3125094392","https://openalex.org/W3148740534","https://openalex.org/W3184586974","https://openalex.org/W3202856983","https://openalex.org/W4200081317","https://openalex.org/W4214588671","https://openalex.org/W4214717370","https://openalex.org/W4241653265","https://openalex.org/W4303437762","https://openalex.org/W4317951323","https://openalex.org/W4362722548","https://openalex.org/W4386446647"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{".We":[0],"propose":[1],"a":[2,55,88],"novel":[3],"framework":[4],"to":[5,53,77],"solve":[6],"risk-sensitive":[7,89],"reinforcement":[8,109],"learning":[9,110],"problems":[10],"where":[11],"the":[12,22,40,113],"agent":[13],"optimizes":[14],"time-consistent":[15],"dynamic":[16,58,70],"spectral":[17,59,71],"risk":[18,60,72,135],"measures.":[19],"Based":[20],"on":[21,129],"notion":[23],"of":[24,57],"conditional":[25],"elicitability,":[26],"our":[27,106],"methodology":[28],"constructs":[29],"(strictly":[30],"consistent)":[31],"scoring":[32,138],"functions":[33],"that":[34,68,92],"are":[35],"used":[36],"as":[37],"penalizers":[38],"in":[39,121],"estimation":[41],"procedure.":[42],"Our":[43],"contribution":[44],"is":[45],"threefold:":[46],"we":[47],"(i)":[48],"devise":[49],"an":[50],"efficient":[51],"approach":[52,116],"estimate":[54],"class":[56],"measures":[61,73],"with":[62,112],"deep":[63,82],"neural":[64,83],"networks,":[65,84],"(ii)":[66],"prove":[67],"these":[69],"may":[74],"be":[75],"approximated":[76],"any":[78,100],"arbitrary":[79],"accuracy":[80],"using":[81],"and":[85,96,117,126,132],"(iii)":[86],"develop":[87],"actor-critic":[90],"algorithm":[91,111],"uses":[93],"full":[94],"episodes":[95],"does":[97],"not":[98],"require":[99],"additional":[101],"nested":[102,114],"transitions.":[103],"We":[104],"compare":[105],"conceptually":[107],"improved":[108],"simulation":[115],"illustrate":[118],"its":[119],"performance":[120],"two":[122],"settings:":[123],"statistical":[124],"arbitrage":[125],"portfolio":[127],"allocation":[128],"both":[130],"simulated":[131],"real":[133],"data.Keywordsdynamic":[134],"measuresreinforcement":[136],"learningelicitabilityconsistent":[137],"functionstime-consistencyactor-critic":[139],"algorithmportfolio":[140],"allocationstatistical":[141],"arbitrageMSC":[142],"codes68T3791-0891G1091G7093E35":[143]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}