{"id":"https://openalex.org/W2058324982","doi":"https://doi.org/10.1109/adprl.2014.7010645","title":"Beyond exponential utility functions: A variance-adjusted approach for risk-averse reinforcement learning","display_name":"Beyond exponential utility functions: A variance-adjusted approach for risk-averse reinforcement learning","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2058324982","doi":"https://doi.org/10.1109/adprl.2014.7010645","mag":"2058324982"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2014.7010645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","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/A5053889549","display_name":"Abhijit Gosavi","orcid":"https://orcid.org/0000-0002-9703-4076"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abhijit A. Gosavi","raw_affiliation_strings":["Department of Engineering Management and Systems Engineering, Missouri University of Science and Technology, Rolla, MO"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Management and Systems Engineering, Missouri University of Science and Technology, Rolla, MO","institution_ids":["https://openalex.org/I20382870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050881965","display_name":"Sajal K. Das","orcid":"https://orcid.org/0000-0002-9471-0868"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sajal K. Das","raw_affiliation_strings":["Department of Computer Science, Missouri University of Science and Technology, Rolla, MO"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Missouri University of Science and Technology, Rolla, MO","institution_ids":["https://openalex.org/I20382870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083526451","display_name":"Susan L. Murray","orcid":"https://orcid.org/0000-0003-0985-3854"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Susan L. Murray","raw_affiliation_strings":["Department of Engineering Management and Systems Engineering, Missouri University of Science and Technology, Rolla, MO"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Management and Systems Engineering, Missouri University of Science and Technology, Rolla, MO","institution_ids":["https://openalex.org/I20382870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053889549"],"corresponding_institution_ids":["https://openalex.org/I20382870"],"apc_list":null,"apc_paid":null,"fwci":0.409,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.74242667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9968000054359436,"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":0.9968000054359436,"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":0.989799976348877,"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/T10315","display_name":"Decision-Making and Behavioral Economics","score":0.98089998960495,"subfield":{"id":"https://openalex.org/subfields/1800","display_name":"General Decision Sciences"},"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":0.8082816004753113},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6639260053634644},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6462339162826538},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6220219731330872},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.58758145570755},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5561672449111938},{"id":"https://openalex.org/keywords/iterated-function","display_name":"Iterated function","score":0.5455025434494019},{"id":"https://openalex.org/keywords/exponential-function","display_name":"Exponential function","score":0.5280552506446838},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5229693055152893},{"id":"https://openalex.org/keywords/cumulative-prospect-theory","display_name":"Cumulative prospect theory","score":0.4906288683414459},{"id":"https://openalex.org/keywords/expected-utility-hypothesis","display_name":"Expected utility hypothesis","score":0.4802146852016449},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4618067145347595},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.30795910954475403},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2761204242706299},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23436763882637024},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23389208316802979},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.11699095368385315},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08547058701515198}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8082816004753113},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6639260053634644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6462339162826538},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6220219731330872},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.58758145570755},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5561672449111938},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.5455025434494019},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.5280552506446838},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5229693055152893},{"id":"https://openalex.org/C2779449553","wikidata":"https://www.wikidata.org/wiki/Q5194187","display_name":"Cumulative prospect theory","level":3,"score":0.4906288683414459},{"id":"https://openalex.org/C205706631","wikidata":"https://www.wikidata.org/wiki/Q2319304","display_name":"Expected utility hypothesis","level":2,"score":0.4802146852016449},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4618067145347595},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.30795910954475403},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2761204242706299},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23436763882637024},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23389208316802979},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.11699095368385315},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08547058701515198},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/adprl.2014.7010645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W129373126","https://openalex.org/W134786152","https://openalex.org/W1534175858","https://openalex.org/W1557760016","https://openalex.org/W1576452626","https://openalex.org/W1585575029","https://openalex.org/W1589395967","https://openalex.org/W1626155273","https://openalex.org/W1980079915","https://openalex.org/W1997933673","https://openalex.org/W1998645260","https://openalex.org/W2001009060","https://openalex.org/W2021693949","https://openalex.org/W2024928738","https://openalex.org/W2036694592","https://openalex.org/W2057510529","https://openalex.org/W2077343054","https://openalex.org/W2088413745","https://openalex.org/W2098432798","https://openalex.org/W2100353677","https://openalex.org/W2107289230","https://openalex.org/W2124684414","https://openalex.org/W2128661050","https://openalex.org/W2139914196","https://openalex.org/W2144446635","https://openalex.org/W2169206416","https://openalex.org/W2173945562","https://openalex.org/W2505159842","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W3022853033","https://openalex.org/W3122210430","https://openalex.org/W3124527335","https://openalex.org/W3139984405","https://openalex.org/W3147321350","https://openalex.org/W4288079541","https://openalex.org/W4301630257","https://openalex.org/W6605301542","https://openalex.org/W6807091881"],"related_works":["https://openalex.org/W3122651444","https://openalex.org/W2112868527","https://openalex.org/W2792368695","https://openalex.org/W2152670157","https://openalex.org/W2170600561","https://openalex.org/W3146182631","https://openalex.org/W3152310311","https://openalex.org/W2808418668","https://openalex.org/W3105579180","https://openalex.org/W1574958246"],"abstract_inverted_index":{"Utility":[0],"theory":[1],"has":[2,32,151],"served":[3],"as":[4,38,67],"a":[5,51,111,122,149,165,175,185],"bedrock":[6],"for":[7,18,42,88,132],"modeling":[8],"risk":[9,13,61],"in":[10,16,35,70,86,141,148,194],"economics.":[11],"Where":[12],"is":[14,174],"involved":[15],"decision-making,":[17],"solving":[19],"Markov":[20],"decision":[21],"processes":[22],"(MDPs)":[23],"via":[24],"utility":[25,29],"theory,":[26],"the":[27,36,60,64,73,98,106,128,136,142,170,180,189,192],"exponential":[28],"(EU)":[30],"function":[31,41,48,100,130],"been":[33],"used":[34,140],"literature":[37],"an":[39],"objective":[40,131],"capturing":[43],"risk-averse":[44],"behavior.":[45],"The":[46,145],"EU":[47,74,129],"framework":[49,75,147],"uses":[50],"so-called":[52],"risk-averseness":[53],"coefficient":[54],"(RAC)":[55],"that":[56,80],"seeks":[57],"to":[58,114],"quantify":[59],"appetite":[62],"of":[63,135,179,188,191],"decision-maker.":[65],"Unfortunately,":[66],"we":[68,118],"show":[69,119],"this":[71],"paper,":[72],"suffers":[76],"from":[77,83],"computational":[78],"deficiencies":[79],"prevent":[81],"it":[82],"being":[84],"useful":[85],"practice":[87],"solution":[89],"methods":[90],"based":[91],"on":[92,164,169],"reinforcement":[93],"learning":[94],"(RL).":[95],"In":[96],"particular,":[97],"value":[99],"becomes":[101],"very":[102],"large":[103],"and":[104,157],"typically":[105],"computer":[107],"overflows.":[108],"We":[109,160,182],"provide":[110],"simple":[112],"example":[113],"demonstrate":[115],"this.":[116],"Further,":[117],"empirically":[120],"how":[121],"variance-adjusted":[123],"(VA)":[124],"approach,":[125],"which":[126,173],"approximates":[127],"reasonable":[133],"values":[134],"RAC,":[137],"can":[138],"be":[139],"RL":[143,167],"algorithm.":[144,196],"VA":[146],"sense":[150],"two":[152],"objectives:":[153],"maximize":[154],"expected":[155],"returns":[156],"minimize":[158],"variance.":[159],"conduct":[161],"empirical":[162],"studies":[163],"VA-based":[166],"algorithm":[168],"semi-MDP":[171],"(SMDP),":[172],"more":[176],"general":[177],"version":[178],"MDP.":[181],"conclude":[183],"with":[184],"mathematical":[186],"proof":[187],"boundedness":[190],"iterates":[193],"our":[195]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}