{"id":"https://openalex.org/W2186820913","doi":"https://doi.org/10.5555/2627435.2750356","title":"Multi-objective reinforcement learning using sets of pareto dominating policies","display_name":"Multi-objective reinforcement learning using sets of pareto dominating policies","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2186820913","doi":"https://doi.org/10.5555/2627435.2750356","mag":"2186820913"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.913.4661","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.913.4661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://jmlr.org/papers/volume15/vanmoffaert14a/vanmoffaert14a.pdf","raw_type":"text"},"type":"article","indexed_in":[],"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":["Dept. of Computer Science, Vrije Universiteit Brussel, Brussels, Belgium#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, Vrije Universiteit Brussel, Brussels, Belgium#TAB#","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":["Dept. of Computer Science, Vrije Universiteit Brussel, Brussels, Belgium#TAB#"],"raw_orcid":"https://orcid.org/0000-0001-6346-4564","affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, Vrije Universiteit Brussel, Brussels, Belgium#TAB#","institution_ids":["https://openalex.org/I13469542"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5075504072"],"corresponding_institution_ids":["https://openalex.org/I13469542"],"apc_list":null,"apc_paid":null,"fwci":9.1397,"has_fulltext":false,"cited_by_count":239,"citation_normalized_percentile":{"value":0.98407243,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"15","issue":"1","first_page":"3483","last_page":"3512"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9965999722480774,"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"}},"topics":[{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9965999722480774,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9937000274658203,"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/T11954","display_name":"Energy Efficiency and Management","score":0.927299976348877,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7947313189506531},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.7063518762588501},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6012963652610779},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5335431694984436},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4821836054325104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46776267886161804},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4415281414985657},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.41338881850242615},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.4106597900390625},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3901621997356415},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2692912817001343},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.12981531023979187}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7947313189506531},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.7063518762588501},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6012963652610779},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5335431694984436},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4821836054325104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46776267886161804},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4415281414985657},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.41338881850242615},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.4106597900390625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3901621997356415},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2692912817001343},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.12981531023979187},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.913.4661","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.913.4661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://jmlr.org/papers/volume15/vanmoffaert14a/vanmoffaert14a.pdf","raw_type":"text"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:90648","is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/multiobjective-reinforcement-learning-using-sets-of-pareto-dominating-policies(14ad8422-075d-4011-842d-44454f451d55).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":"","raw_type":"article"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:98394","is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/multiobjective-reinforcement-learning-using-sets-of-pareto-dominating-policies(3563e329-da53-48bc-975f-95afe914b485).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":"","raw_type":"article"},{"id":"mag:2186820913","is_oa":false,"landing_page_url":"http://jmlr.csail.mit.edu/papers/volume15/vanmoffaert14a/vanmoffaert14a.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Journal of Machine Learning Research","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W42649658","https://openalex.org/W288089086","https://openalex.org/W291243768","https://openalex.org/W1482041209","https://openalex.org/W1515851193","https://openalex.org/W1543572792","https://openalex.org/W1834963927","https://openalex.org/W1974819972","https://openalex.org/W2012612381","https://openalex.org/W2029512498","https://openalex.org/W2038420231","https://openalex.org/W2058192020","https://openalex.org/W2060846151","https://openalex.org/W2067956254","https://openalex.org/W2071279638","https://openalex.org/W2090218528","https://openalex.org/W2097031964","https://openalex.org/W2098907614","https://openalex.org/W2116001481","https://openalex.org/W2117428849","https://openalex.org/W2117626647","https://openalex.org/W2121863487","https://openalex.org/W2126105956","https://openalex.org/W2141481921","https://openalex.org/W2147750403","https://openalex.org/W2152213878","https://openalex.org/W2160088187","https://openalex.org/W2167062306","https://openalex.org/W2994964425","https://openalex.org/W3011120880","https://openalex.org/W3103262232"],"related_works":["https://openalex.org/W3103262232","https://openalex.org/W2121863487","https://openalex.org/W2012612381","https://openalex.org/W2060846151","https://openalex.org/W2141481921","https://openalex.org/W1987725948","https://openalex.org/W2145339207","https://openalex.org/W2117428849","https://openalex.org/W1543572792","https://openalex.org/W2117626647","https://openalex.org/W2257979135","https://openalex.org/W1998649829","https://openalex.org/W2173248099","https://openalex.org/W2126105956","https://openalex.org/W2123516968","https://openalex.org/W2058192020","https://openalex.org/W288089086","https://openalex.org/W2155027007","https://openalex.org/W1757796397","https://openalex.org/W2167062306"],"abstract_inverted_index":{"Many":[0],"real-world":[1],"problems":[2],"involve":[3],"the":[4,23,41,64,119,140,146,160,165,170],"optimization":[5],"of":[6,18,43,83,115,125,128,148],"multiple,":[7],"possibly":[8],"conflicting":[9],"ob-jectives.":[10],"Multi-objective":[11],"reinforcement":[12,20,70],"learning":[13,21,44,60,71],"(MORL)":[14],"is":[15,27,40,75,99,118,135],"a":[16,56,69,76,81,88,136],"generalization":[17],"standard":[19],"where":[22],"scalar":[24],"reward":[25,143,152],"signal":[26],"extended":[28],"to":[29,158,163],"multiple":[30,48],"feedback":[31],"signals,":[32],"in":[33,87,101,132],"essence,":[34],"one":[35],"for":[36],"each":[37],"objective.":[38],"MORL":[39],"process":[42],"policies":[45,86,167],"that":[46,62,79,122,138],"optimize":[47],"criteria":[49],"simultaneously.":[50],"In":[51],"this":[52,93,133],"paper,":[53],"we":[54],"present":[55],"novel":[57],"temporal":[58],"differ-ence":[59],"algorithm":[61,74,78,94],"integrates":[63],"Pareto":[65,84,95,116],"dominance":[66],"relation":[67],"into":[68],"approach.":[72],"This":[73,154],"multi-policy":[77],"learns":[80],"set":[82,147],"dominating":[85],"single":[89],"run.":[90],"We":[91],"name":[92],"Q-learning":[96,117],"and":[97,162,176],"it":[98],"applicable":[100],"episodic":[102],"environments":[103],"with":[104],"deterministic":[105],"as":[106,108],"well":[107],"stochastic":[109],"transition":[110],"func-tions.":[111],"A":[112],"crucial":[113],"aspect":[114],"updating":[120],"mechanism":[121,137],"bootstraps":[123],"sets":[124,161],"Q-vectors.":[126],"One":[127],"our":[129],"main":[130],"contributions":[131],"paper":[134],"sep-arates":[139],"expected":[141,149],"immediate":[142],"vector":[144],"from":[145],"future":[150],"discounted":[151],"vectors.":[153],"decomposition":[155],"allows":[156],"us":[157],"update":[159],"exploit":[164],"learned":[166],"consistently":[168],"throughout":[169],"state":[171],"space.":[172],"To":[173],"balance":[174],"exploration":[175],"exploitation":[177]},"counts_by_year":[{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":30},{"year":2023,"cited_by_count":40},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":26},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":4}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}