{"id":"https://openalex.org/W2060846151","doi":"https://doi.org/10.1109/adprl.2013.6615007","title":"Scalarized multi-objective reinforcement learning: Novel design techniques","display_name":"Scalarized multi-objective reinforcement learning: Novel design techniques","publication_year":2013,"publication_date":"2013-04-01","ids":{"openalex":"https://openalex.org/W2060846151","doi":"https://doi.org/10.1109/adprl.2013.6615007","mag":"2060846151"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2013.6615007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2013.6615007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 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/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 Comput. Sci., Vrije Univ. Brussel, Brussels, 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 Comput. Sci., Vrije Univ. Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016131956","display_name":"M\u0103d\u0103lina M. Drugan","orcid":"https://orcid.org/0000-0001-9497-3134"},"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":"Madalina M. Drugan","raw_affiliation_strings":["Department of Computer Science, Vrije Universiteit Brussel, Brussels, Belgium","Dept. of Comput. Sci., Vrije Univ. Brussel, Brussels, 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 Comput. Sci., Vrije Univ. Brussel, Brussels, 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 Nowe","raw_affiliation_strings":["Department of Computer Science, Vrije Universiteit Brussel, Brussels, Belgium","Dept. of Comput. Sci., Vrije Univ. Brussel, Brussels, 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 Comput. Sci., Vrije Univ. Brussel, Brussels, 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":8.2052,"has_fulltext":false,"cited_by_count":248,"citation_normalized_percentile":{"value":0.97975864,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"191","last_page":"199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9645000100135803,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9093999862670898,"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/mathematical-optimization","display_name":"Mathematical optimization","score":0.6814744472503662},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5768141150474548},{"id":"https://openalex.org/keywords/chebyshev-filter","display_name":"Chebyshev filter","score":0.514840304851532},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.5115402936935425},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.4800618588924408},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4773285984992981},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4757145047187805},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.46777358651161194},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4571809768676758},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.42319566011428833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26158154010772705}],"concepts":[{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6814744472503662},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5768141150474548},{"id":"https://openalex.org/C21424316","wikidata":"https://www.wikidata.org/wiki/Q718621","display_name":"Chebyshev filter","level":2,"score":0.514840304851532},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.5115402936935425},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.4800618588924408},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4773285984992981},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4757145047187805},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46777358651161194},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4571809768676758},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.42319566011428833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26158154010772705},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/adprl.2013.6615007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2013.6615007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:publications/f025b3c0-b3df-45b7-9897-a550213fc254","is_oa":false,"landing_page_url":"https://research.tue.nl/en/publications/f025b3c0-b3df-45b7-9897-a550213fc254","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Van Moffaert, K, Drugan, M M & Nowe, A 2013, Scalarized multi-objective reinforcement learning : novel design techniques. in 2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL) : 16 - 19 April 2013, Singapore. Institute of Electrical and Electronics Engineers, Piscataway, pp. 191-199, 2013 IEEE Symposium on Adaptive Dynamic Programming And Reinforcement Learning (ADPRL 2013), Singapore, Singapore, 16/04/13. https://doi.org/10.1109/ADPRL.2013.6615007","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:tue:oai:pure.tue.nl:publications/f025b3c0-b3df-45b7-9897-a550213fc254","is_oa":false,"landing_page_url":"https://research.tue.nl/nl/publications/f025b3c0-b3df-45b7-9897-a550213fc254","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL) : 16 - 19 April 2013, Singapore, 191 - 199","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W291243768","https://openalex.org/W2012612381","https://openalex.org/W2030435702","https://openalex.org/W2058192020","https://openalex.org/W2106334424","https://openalex.org/W2107471880","https://openalex.org/W2117428849","https://openalex.org/W2126105956","https://openalex.org/W2141481921","https://openalex.org/W2152213878","https://openalex.org/W2155063211","https://openalex.org/W3011120880","https://openalex.org/W4213124581","https://openalex.org/W6610454638","https://openalex.org/W6839976737"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2390710574","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090"],"abstract_inverted_index":{"In":[0],"multi-objective":[1,24,95],"problems,":[2],"it":[3,35,111],"is":[4,18,36,67,72,146],"key":[5],"to":[6,21],"find":[7,45],"compromising":[8],"solutions":[9,46,117,143],"that":[10,38],"balance":[11],"different":[12],"objectives.":[13],"The":[14,98],"linear":[15,41,107],"scalarization":[16,80,85,100,108],"function":[17,109],"often":[19,73],"utilized":[20],"translate":[22],"the":[23,51,56,62,65,74,83,103,106,120,123,138,151],"nature":[25],"of":[26,50,64,105,119,122,140],"a":[27,30,78,88,134],"problem":[28],"into":[29],"standard,":[31],"single-objective":[32],"problem.":[33],"Generally,":[34],"noted":[37],"such":[39],"as":[40,71,87,110,127,129],"combination":[42],"can":[43,112],"only":[44],"in":[47,59,94],"convex":[48,126],"areas":[49],"Pareto":[52,115,141],"front,":[53,124],"therefore":[54],"making":[55],"method":[57,101],"inapplicable":[58],"situations":[60],"where":[61],"shape":[63,121],"front":[66],"not":[68,147],"known":[69],"beforehand,":[70],"case.":[75],"We":[76],"propose":[77],"non-linear":[79],"function,":[81,86],"called":[82],"Chebyshev":[84,99],"basis":[89],"for":[90],"action":[91],"selection":[92],"strategies":[93],"reinforcement":[96],"learning.":[97],"overcomes":[102],"flaws":[104],"(i)":[113],"discover":[114],"optimal":[116,142],"regardless":[118],"i.e.":[125],"well":[128],"non-convex":[130],",":[131],"(ii)":[132],"obtain":[133],"better":[135],"spread":[136],"amongst":[137],"set":[139],"and":[144],"(iii)":[145],"particularly":[148],"dependent":[149],"on":[150],"actual":[152],"weights":[153],"used.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":40},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":28},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":35},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":1}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}