{"id":"https://openalex.org/W4294690570","doi":"https://doi.org/10.23919/acc53348.2022.9867841","title":"Embracing Risk in Reinforcement Learning: The Connection between Risk-Sensitive Exponential and Distributionally Robust Criteria","display_name":"Embracing Risk in Reinforcement Learning: The Connection between Risk-Sensitive Exponential and Distributionally Robust Criteria","publication_year":2022,"publication_date":"2022-06-08","ids":{"openalex":"https://openalex.org/W4294690570","doi":"https://doi.org/10.23919/acc53348.2022.9867841"},"language":"en","primary_location":{"id":"doi:10.23919/acc53348.2022.9867841","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867841","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","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 American Control Conference (ACC)","raw_type":"proceedings-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/A5051837539","display_name":"Erfaun Noorani","orcid":"https://orcid.org/0000-0002-5171-122X"},"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":true,"raw_author_name":"Erfaun Noorani","raw_affiliation_strings":["Institute for System Research (ISR) at the University of Maryland College Park,Department of Electrical and Computer Engineering,College Park,MD,USA","Department of Electrical and Computer Engineering, Institute for System Research (ISR) at the University of Maryland College Park, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"Institute for System Research (ISR) at the University of Maryland College Park,Department of Electrical and Computer Engineering,College Park,MD,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Institute for System Research (ISR) at the University of Maryland College Park, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044395526","display_name":"John S. Baras","orcid":"https://orcid.org/0000-0002-4955-8561"},"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":"John S. Baras","raw_affiliation_strings":["Institute for System Research (ISR) at the University of Maryland College Park,Department of Electrical and Computer Engineering,College Park,MD,USA","Department of Electrical and Computer Engineering, Institute for System Research (ISR) at the University of Maryland College Park, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"Institute for System Research (ISR) at the University of Maryland College Park,Department of Electrical and Computer Engineering,College Park,MD,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Institute for System Research (ISR) at the University of Maryland College Park, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051837539"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":2.0865,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.8809766,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2703","last_page":"2708"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.9745000004768372,"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":0.9745000004768372,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9745000004768372,"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/T11413","display_name":"Risk and Portfolio Optimization","score":0.9553999900817871,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8823421001434326},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6481403708457947},{"id":"https://openalex.org/keywords/exponential-function","display_name":"Exponential function","score":0.6310970783233643},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5802177786827087},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.48322996497154236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4709295332431793},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.44398459792137146},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4413226246833801},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.42967358231544495},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41831281781196594},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23416340351104736},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1322721540927887}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8823421001434326},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6481403708457947},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.6310970783233643},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5802177786827087},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.48322996497154236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4709295332431793},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.44398459792137146},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4413226246833801},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.42967358231544495},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41831281781196594},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23416340351104736},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1322721540927887},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc53348.2022.9867841","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867841","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","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 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W51049863","https://openalex.org/W112736823","https://openalex.org/W1511986666","https://openalex.org/W1515828703","https://openalex.org/W1517329556","https://openalex.org/W1528703258","https://openalex.org/W1771410628","https://openalex.org/W1968793942","https://openalex.org/W1969897341","https://openalex.org/W1972633005","https://openalex.org/W1986478300","https://openalex.org/W1993411524","https://openalex.org/W2013050310","https://openalex.org/W2031355801","https://openalex.org/W2041946752","https://openalex.org/W2046396733","https://openalex.org/W2054321814","https://openalex.org/W2059120410","https://openalex.org/W2075868924","https://openalex.org/W2096035449","https://openalex.org/W2098774185","https://openalex.org/W2106929622","https://openalex.org/W2119567691","https://openalex.org/W2120340025","https://openalex.org/W2127082526","https://openalex.org/W2145060720","https://openalex.org/W2145339207","https://openalex.org/W2162849300","https://openalex.org/W2310516540","https://openalex.org/W2602963933","https://openalex.org/W2736601468","https://openalex.org/W2773525213","https://openalex.org/W2781726626","https://openalex.org/W2785738552","https://openalex.org/W2793745738","https://openalex.org/W2887443568","https://openalex.org/W2914994663","https://openalex.org/W2947052139","https://openalex.org/W2949207039","https://openalex.org/W2949561945","https://openalex.org/W2950300520","https://openalex.org/W3003521509","https://openalex.org/W3101725915","https://openalex.org/W4210564515","https://openalex.org/W4210869902","https://openalex.org/W4214717370","https://openalex.org/W4288359673","https://openalex.org/W4298857966","https://openalex.org/W6604547463","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6674884181","https://openalex.org/W6681439324","https://openalex.org/W6683517036","https://openalex.org/W6734517396","https://openalex.org/W6735677848","https://openalex.org/W6741002519","https://openalex.org/W6747027214","https://openalex.org/W6747473740","https://openalex.org/W6747924173","https://openalex.org/W6750134565","https://openalex.org/W6753994356","https://openalex.org/W6757021410","https://openalex.org/W6759312646","https://openalex.org/W6763184490","https://openalex.org/W6764339904"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"We":[0],"explore":[1],"the":[2,5,26,52,60,72,81],"relation":[3],"between":[4],"risk-sensitive":[6,56,76],"exponential":[7,57,86],"(exponential":[8],"of":[9,25,39,55,75,85],"total":[10],"cost)":[11],"and":[12,18,49],"Distributionally":[13],"Robust":[14],"Reinforcement":[15,28,41,61,77,92],"Learning":[16,29,42,62,78,93],"objectives,":[17],"in":[19,59,65,80],"doing":[20],"so,":[21],"we":[22],"unify":[23],"some":[24],"popular":[27],"algorithms.":[30],"Such":[31],"equivalence":[32],"(I)":[33],"allows":[34],"to":[35],"understand":[36],"a":[37,45,68],"number":[38],"well-known":[40],"algorithms":[43,79,94],"from":[44],"risk":[46],"minimization":[47],"perspective":[48],"(II)":[50],"establishes":[51],"robustness":[53,84],"properties":[54],"objective":[58],"context,":[63],"which":[64],"turn":[66],"provides":[67],"theoretical":[69],"justification":[70],"for":[71],"robust":[73],"performance":[74],"literature.":[82],"The":[83],"criteria":[87],"motivates":[88],"risk-sensitizing":[89],"current":[90],"risk-neutral":[91],"using":[95],"such":[96],"criteria.":[97]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}