{"id":"https://openalex.org/W4315488728","doi":"https://doi.org/10.1109/cdc51059.2022.9992450","title":"Risk-Averse Reinforcement Learning via Dynamic Time-Consistent Risk Measures","display_name":"Risk-Averse Reinforcement Learning via Dynamic Time-Consistent Risk Measures","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4315488728","doi":"https://doi.org/10.1109/cdc51059.2022.9992450"},"language":"en","primary_location":{"id":"doi:10.1109/cdc51059.2022.9992450","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9992450","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","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 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2301.05981","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016835982","display_name":"Xian Yu","orcid":"https://orcid.org/0000-0003-1059-5303"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xian Yu","raw_affiliation_strings":["The Ohio State University,Department of Integrated Systems Engineering,Columbus,Ohio,USA","Department of Integrated Systems Engineering, The Ohio State University, Columbus, Ohio, USA"],"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Integrated Systems Engineering,Columbus,Ohio,USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Integrated Systems Engineering, The Ohio State University, Columbus, Ohio, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029271681","display_name":"Siqian Shen","orcid":"https://orcid.org/0000-0002-2854-163X"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siqian Shen","raw_affiliation_strings":["University of Michigan,Department of Industrial and Operations Engineering,Ann Arbor,Michigan,USA","Department of Industrial and Operations Engineering, University of Michigan, Ann Arbor, Michigan, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Industrial and Operations Engineering,Ann Arbor,Michigan,USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Department of Industrial and Operations Engineering, University of Michigan, Ann Arbor, Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5016835982"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.1044,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.35076842,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2307","last_page":"2312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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":0.998199999332428,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9690999984741211,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9656999707221985,"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":0.8105461597442627},{"id":"https://openalex.org/keywords/cvar","display_name":"CVAR","score":0.7760927677154541},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.753033459186554},{"id":"https://openalex.org/keywords/time-consistency","display_name":"Time consistency","score":0.6697838306427002},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6058825850486755},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.5591685175895691},{"id":"https://openalex.org/keywords/expected-shortfall","display_name":"Expected shortfall","score":0.5588583946228027},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5407015085220337},{"id":"https://openalex.org/keywords/risk-measure","display_name":"Risk measure","score":0.5091971755027771},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5091096758842468},{"id":"https://openalex.org/keywords/dynamic-risk-measure","display_name":"Dynamic risk measure","score":0.48069292306900024},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3722727298736572},{"id":"https://openalex.org/keywords/risk-management","display_name":"Risk management","score":0.2648848593235016},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25518542528152466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19160348176956177},{"id":"https://openalex.org/keywords/actuarial-science","display_name":"Actuarial science","score":0.14639884233474731},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.11939668655395508},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09271159768104553},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.08808758854866028}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8105461597442627},{"id":"https://openalex.org/C2779922397","wikidata":"https://www.wikidata.org/wiki/Q5014755","display_name":"CVAR","level":4,"score":0.7760927677154541},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.753033459186554},{"id":"https://openalex.org/C11534374","wikidata":"https://www.wikidata.org/wiki/Q7805280","display_name":"Time consistency","level":2,"score":0.6697838306427002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6058825850486755},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.5591685175895691},{"id":"https://openalex.org/C5496284","wikidata":"https://www.wikidata.org/wiki/Q5420856","display_name":"Expected shortfall","level":3,"score":0.5588583946228027},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5407015085220337},{"id":"https://openalex.org/C2781472820","wikidata":"https://www.wikidata.org/wiki/Q2154759","display_name":"Risk measure","level":3,"score":0.5091971755027771},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5091096758842468},{"id":"https://openalex.org/C167548438","wikidata":"https://www.wikidata.org/wiki/Q5319012","display_name":"Dynamic risk measure","level":4,"score":0.48069292306900024},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3722727298736572},{"id":"https://openalex.org/C32896092","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Risk management","level":2,"score":0.2648848593235016},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25518542528152466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19160348176956177},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.14639884233474731},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.11939668655395508},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09271159768104553},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.08808758854866028},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cdc51059.2022.9992450","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9992450","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","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 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2301.05981","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.05981","pdf_url":"https://arxiv.org/pdf/2301.05981","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2301.05981","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.05981","pdf_url":"https://arxiv.org/pdf/2301.05981","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3657849781","display_name":null,"funder_award_id":"-SC0018018","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6744698226","display_name":null,"funder_award_id":"DE-SC0018018","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320309652","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4315488728.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W134786152","https://openalex.org/W579853240","https://openalex.org/W1491517969","https://openalex.org/W1522301498","https://openalex.org/W1541527977","https://openalex.org/W1647779468","https://openalex.org/W1965878388","https://openalex.org/W1976658031","https://openalex.org/W1990259848","https://openalex.org/W2001009060","https://openalex.org/W2019291268","https://openalex.org/W2060248504","https://openalex.org/W2088413745","https://openalex.org/W2089786171","https://openalex.org/W2108888882","https://openalex.org/W2136503687","https://openalex.org/W2139914196","https://openalex.org/W2141203641","https://openalex.org/W2145339207","https://openalex.org/W2152790647","https://openalex.org/W2155153696","https://openalex.org/W2162849300","https://openalex.org/W2165428239","https://openalex.org/W2168565265","https://openalex.org/W2170838015","https://openalex.org/W2522885171","https://openalex.org/W2782965505","https://openalex.org/W2949207039","https://openalex.org/W2949963197","https://openalex.org/W2954940391","https://openalex.org/W2962850106","https://openalex.org/W3041202696","https://openalex.org/W3124407081","https://openalex.org/W3125145310","https://openalex.org/W3126605566","https://openalex.org/W4214717370","https://openalex.org/W4237591687","https://openalex.org/W4247165901","https://openalex.org/W4298023569","https://openalex.org/W4298857966","https://openalex.org/W6629397718","https://openalex.org/W6631190155","https://openalex.org/W6637967152","https://openalex.org/W6680547686","https://openalex.org/W6683517036"],"related_works":["https://openalex.org/W2384833971","https://openalex.org/W2499931925","https://openalex.org/W1997933673","https://openalex.org/W3180712247","https://openalex.org/W3125265748","https://openalex.org/W2408851247","https://openalex.org/W2291382242","https://openalex.org/W2351484155","https://openalex.org/W3121825436","https://openalex.org/W3173705157"],"abstract_inverted_index":{"Traditional":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"aims":[4],"to":[5,18,21,59],"maximize":[6],"the":[7,12,34,53,60,88,102,109,119,145,150,156],"expected":[8],"total":[9],"reward,":[10],"while":[11],"risk":[13,39,84],"of":[14,36,40,43,73,121,155],"uncertain":[15],"outcomes":[16],"needs":[17],"be":[19],"controlled":[20],"ensure":[22],"reliable":[23],"performance":[24],"in":[25,45],"a":[26,41,70,80,92,114,129],"risk-averse":[27,62,89,130,146],"setting.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32,86,127],"consider":[33],"problem":[35],"maximizing":[37],"dynamic":[38],"sequence":[42],"rewards":[44],"infinite-horizon":[46,61],"Markov":[47],"Decision":[48],"Processes":[49],"(MDPs).":[50],"We":[51,105],"adapt":[52],"Expected":[54],"Conditional":[55],"Risk":[56],"Measures":[57],"(ECRMs)":[58],"MDP":[63,90],"and":[64,75,99,134,152],"prove":[65,107],"its":[66],"time":[67],"consistency.":[68],"Using":[69],"convex":[71],"combination":[72],"expectation":[74],"conditional":[76,83],"value-at-risk":[77],"(CVaR)":[78],"as":[79,91],"special":[81],"one-step":[82],"measure,":[85],"reformulate":[87],"risk-neutral":[93],"counterpart":[94],"with":[95],"augmented":[96],"action":[97],"space":[98],"manipulation":[100],"on":[101,139],"immediate":[103],"rewards.":[104],"further":[106],"that":[108,144],"related":[110],"Bellman":[111],"operator":[112],"is":[113],"contraction":[115],"mapping,":[116],"which":[117],"guarantees":[118],"convergence":[120],"any":[122],"value-based":[123],"RL":[124],"algorithms.":[125],"Accordingly,":[126],"develop":[128],"deep":[131],"Q-learning":[132],"framework,":[133],"our":[135],"numerical":[136],"studies":[137],"based":[138],"two":[140],"simple":[141],"MDPs":[142],"show":[143],"setting":[147],"can":[148],"reduce":[149],"variance":[151],"enhance":[153],"robustness":[154],"results.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}