{"id":"https://openalex.org/W1556201700","doi":"https://doi.org/10.1109/cec.2015.7257098","title":"Risk-sensitivity through multi-objective reinforcement learning","display_name":"Risk-sensitivity through multi-objective reinforcement learning","publication_year":2015,"publication_date":"2015-05-01","ids":{"openalex":"https://openalex.org/W1556201700","doi":"https://doi.org/10.1109/cec.2015.7257098","mag":"1556201700"},"language":"en","primary_location":{"id":"doi:10.1109/cec.2015.7257098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec.2015.7257098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Congress on Evolutionary Computation (CEC)","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/A5075504072","display_name":"Kristof Van Moffaert","orcid":null},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Kristof Van Moffaert","raw_affiliation_strings":["Department of Computer Science, Vrije Universiteit Brussel, Brussels, Belgium","Dept. of Computer Science, Vrije Universiteit Brussel, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Dept. of Computer Science, Vrije Universiteit Brussel, Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084002137","display_name":"Tim Brys","orcid":null},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Tim Brys","raw_affiliation_strings":["Department of Computer Science, Vrije Universiteit Brussel, Brussels, Belgium","Dept. of Computer Science, Vrije Universiteit Brussel, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Dept. of Computer Science, Vrije Universiteit Brussel, Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064553018","display_name":"Ann Now\u00e9","orcid":"https://orcid.org/0000-0001-6346-4564"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Ann Now\u00e9","raw_affiliation_strings":["Department of Computer Science, Vrije Universiteit Brussel, Brussels, Belgium","Dept. of Computer Science, Vrije Universiteit Brussel, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Dept. of Computer Science, Vrije Universiteit Brussel, Belgium","institution_ids":["https://openalex.org/I13469542"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5075504072"],"corresponding_institution_ids":["https://openalex.org/I13469542"],"apc_list":null,"apc_paid":null,"fwci":1.3345,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85556122,"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":"1746","last_page":"1753"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9922999739646912,"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":0.8156552910804749},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.7057404518127441},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6930446624755859},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.573203444480896},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5639007687568665},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5099927186965942},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.5000472068786621},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4758048951625824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46882718801498413},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.4537104666233063},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4038221538066864},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16653254628181458},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09770730137825012}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8156552910804749},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.7057404518127441},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6930446624755859},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.573203444480896},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5639007687568665},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5099927186965942},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.5000472068786621},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4758048951625824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46882718801498413},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.4537104666233063},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4038221538066864},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16653254628181458},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09770730137825012},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cec.2015.7257098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec.2015.7257098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:94090","is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/risksensitivity-through-multiobjective-reinforcement-learning(d44a0148-8571-465c-8462-f75d1da34a2e).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"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":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W134786152","https://openalex.org/W173958421","https://openalex.org/W288089086","https://openalex.org/W391985582","https://openalex.org/W1539701879","https://openalex.org/W1543572792","https://openalex.org/W1545918039","https://openalex.org/W1585711251","https://openalex.org/W1833338034","https://openalex.org/W1927597696","https://openalex.org/W1965681731","https://openalex.org/W2002305926","https://openalex.org/W2050149892","https://openalex.org/W2060248504","https://openalex.org/W2060846151","https://openalex.org/W2071279638","https://openalex.org/W2073297125","https://openalex.org/W2101075098","https://openalex.org/W2113496026","https://openalex.org/W2121863487","https://openalex.org/W2141203641","https://openalex.org/W2147750403","https://openalex.org/W2156578004","https://openalex.org/W2157263597","https://openalex.org/W2162849300","https://openalex.org/W2186820913","https://openalex.org/W2313791856","https://openalex.org/W2964108826","https://openalex.org/W3011120880","https://openalex.org/W3106238320","https://openalex.org/W4233696721","https://openalex.org/W4248462665","https://openalex.org/W6632292508","https://openalex.org/W6765793075"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W2069592018","https://openalex.org/W2075740387","https://openalex.org/W4391331176"],"abstract_inverted_index":{"Usually":[0],"in":[1,16,153],"reinforcement":[2],"learning,":[3],"the":[4,7,12,25,37,57,63,91,104,107,137,149],"goal":[5],"of":[6,39,66,95,106,126],"agent":[8],"is":[9,70,79,118,168],"to":[10,49,122,155],"maximize":[11],"expected":[13],"return.":[14],"However,":[15],"practical":[17],"applications,":[18],"algorithms":[19],"that":[20,102,111,130,144],"solely":[21],"focus":[22],"on":[23,72],"maximizing":[24],"mean":[26,165],"return":[27],"could":[28,46],"be":[29,47],"inappropriate":[30],"as":[31],"they":[32],"do":[33],"not":[34],"account":[35],"for":[36,51],"variability":[38,44],"their":[40],"solutions.":[41],"Thereby,":[42],"a":[43,52,75,124,161,171],"measure":[45],"included":[48],"accommodate":[50],"risk-sensitive":[53,115,157],"setting,":[54],"i.e.":[55],"where":[56,74,159],"system":[58],"engineer":[59],"can":[60,139],"explicitly":[61],"define":[62],"tolerated":[64],"level":[65],"variance.":[67],"Our":[68],"approach":[69],"based":[71],"multi-objectivization":[73],"standard":[76,92,156],"single-objective":[77],"environment":[78,97],"extended":[80],"with":[81,98],"one":[82],"(or":[83],"more)":[84],"additional":[85,100],"objectives.":[86,134],"More":[87],"precisely,":[88],"we":[89],"augment":[90],"feedback":[93],"signal":[94],"an":[96,99],"objective":[101],"defines":[103],"variance":[105,167],"solution.":[108],"We":[109],"highlight":[110],"our":[112],"algorithm,":[113],"named":[114],"Pareto":[116,127],"Q-learning,":[117],"(1)":[119],"specifically":[120],"tailored":[121],"learn":[123],"set":[125],"non-dominated":[128],"policies":[129],"trade-off":[131,163],"these":[132],"two":[133],"Additionally":[135],"(2),":[136],"algorithm":[138],"also":[140],"retrieve":[141],"every":[142],"policy":[143],"has":[145],"been":[146],"learned":[147,169],"throughout":[148],"state-action":[150],"space.":[151],"This":[152],"contrast":[154],"approaches":[158],"only":[160],"single":[162],"between":[164],"and":[166],"at":[170],"time.":[172]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}