{"id":"https://openalex.org/W4285289665","doi":"https://doi.org/10.1017/s0269888921000163","title":"An online scalarization multi-objective reinforcement learning algorithm: TOPSIS Q-learning","display_name":"An online scalarization multi-objective reinforcement learning algorithm: TOPSIS Q-learning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285289665","doi":"https://doi.org/10.1017/s0269888921000163"},"language":"en","primary_location":{"id":"doi:10.1017/s0269888921000163","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0269888921000163","pdf_url":null,"source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-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/A5065847002","display_name":"Mohammad Mirzanejad","orcid":"https://orcid.org/0009-0005-0120-4421"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Mohammad Mirzanejad","raw_affiliation_strings":["Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran; e-mail:","e-mail:","Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran; e-mail:","institution_ids":["https://openalex.org/I23946033"]},{"raw_affiliation_string":"e-mail:","institution_ids":[]},{"raw_affiliation_string":"Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100654248","display_name":"Morteza Ebrahimi","orcid":"https://orcid.org/0000-0001-7683-443X"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Morteza Ebrahimi","raw_affiliation_strings":["Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran; e-mail:","e-mail:","Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran; e-mail:","institution_ids":["https://openalex.org/I23946033"]},{"raw_affiliation_string":"e-mail:","institution_ids":[]},{"raw_affiliation_string":"Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080095540","display_name":"Peter Vamplew","orcid":"https://orcid.org/0000-0002-8687-4424"},"institutions":[{"id":"https://openalex.org/I149672521","display_name":"Federation University","ror":"https://ror.org/05qbzwv83","country_code":"AU","type":"education","lineage":["https://openalex.org/I149672521"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Peter Vamplew","raw_affiliation_strings":["School of Engineering, Information Technology and Physical Sciences, Federation University Australia, Ballarat, Australia; e-mail:","e-mail:","School of Engineering, Information Technology and Physical Sciences, Federation University Australia, Ballarat, Australia"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Information Technology and Physical Sciences, Federation University Australia, Ballarat, Australia; e-mail:","institution_ids":["https://openalex.org/I149672521"]},{"raw_affiliation_string":"e-mail:","institution_ids":[]},{"raw_affiliation_string":"School of Engineering, Information Technology and Physical Sciences, Federation University Australia, Ballarat, Australia","institution_ids":["https://openalex.org/I149672521"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035048262","display_name":"Hadi Veisi","orcid":"https://orcid.org/0000-0003-2372-7969"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Hadi Veisi","raw_affiliation_strings":["Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran; e-mail:","e-mail:","Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran; e-mail:","institution_ids":["https://openalex.org/I23946033"]},{"raw_affiliation_string":"e-mail:","institution_ids":[]},{"raw_affiliation_string":"Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5065847002"],"corresponding_institution_ids":["https://openalex.org/I23946033"],"apc_list":null,"apc_paid":null,"fwci":1.6548,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.86229136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"37","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955999851226807,"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":0.9955999851226807,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9783999919891357,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/topsis","display_name":"TOPSIS","score":0.7988605499267578},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7960202693939209},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6412858963012695},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5177627801895142},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.484628289937973},{"id":"https://openalex.org/keywords/ideal","display_name":"Ideal (ethics)","score":0.4690461754798889},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45838209986686707},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.45507848262786865},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4498519003391266},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42811572551727295},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4085053503513336},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2813491225242615},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.1942209005355835}],"concepts":[{"id":"https://openalex.org/C51566761","wikidata":"https://www.wikidata.org/wiki/Q1235853","display_name":"TOPSIS","level":2,"score":0.7988605499267578},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7960202693939209},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6412858963012695},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5177627801895142},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.484628289937973},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.4690461754798889},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45838209986686707},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.45507848262786865},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4498519003391266},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42811572551727295},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4085053503513336},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2813491225242615},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.1942209005355835},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1017/s0269888921000163","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0269888921000163","pdf_url":null,"source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-article"},{"id":"pmh:vital:17417","is_oa":false,"landing_page_url":"http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/189232","pdf_url":null,"source":{"id":"https://openalex.org/S4306400234","display_name":"FedUni ResearchOnline (Federation University Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210158496","host_organization_name":"Australian Federation of University Women \u2013 South Australia","host_organization_lineage":["https://openalex.org/I4210158496"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W47799525","https://openalex.org/W391985582","https://openalex.org/W1982951341","https://openalex.org/W2012612381","https://openalex.org/W2060846151","https://openalex.org/W2102660061","https://openalex.org/W2141481921","https://openalex.org/W2186820913","https://openalex.org/W2506768821","https://openalex.org/W2625332229","https://openalex.org/W2666874989","https://openalex.org/W2759684794","https://openalex.org/W2790759781","https://openalex.org/W3047673486","https://openalex.org/W3127313282","https://openalex.org/W4233696721","https://openalex.org/W6601907869","https://openalex.org/W6677435986","https://openalex.org/W6748627825","https://openalex.org/W7056891567"],"related_works":["https://openalex.org/W2884422668","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2892507673","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W2537866915"],"abstract_inverted_index":{"Abstract":[0],"Conventional":[1],"reinforcement":[2,29],"learning":[3,30],"focuses":[4],"on":[5,99],"problems":[6,12],"with":[7,54,97],"single":[8],"objective.":[9],"However,":[10],"many":[11],"have":[13],"multiple":[14],"objectives":[15,170],"or":[16,23],"criteria":[17,147],"that":[18,50],"may":[19,133],"be":[20,74,135],"independent,":[21],"related,":[22],"contradictory.":[24],"In":[25,86],"such":[26],"cases,":[27],"multi-objective":[28],"is":[31,45,95,117,151],"used":[32,75],"to":[33,40,81,123,182],"propose":[34],"a":[35,46,89,149,187],"compromise":[36],"among":[37],"the":[38,42,52,58,63,67,78,83,110,114,121,125,128,164,178,184,192,196],"solutions":[39],"balance":[41],"objectives.":[43,129,176],"TOPSIS":[44,93],"multi-criteria":[47],"decision":[48,146],"method":[49],"selects":[51],"alternative":[53],"minimum":[55],"distance":[56,65],"from":[57,66],"positive":[59],"ideal":[60,69],"solution":[61,150],"and":[62,148,160,166],"maximum":[64],"negative":[68],"solution,":[70],"so":[71,138],"it":[72],"can":[73,162],"effectively":[76],"in":[77,102,109],"decision-making":[79],"process":[80],"select":[82],"next":[84],"action.":[85],"this":[87],"research":[88],"single-policy":[90,107],"algorithm":[91,185,197],"called":[92],"Q-Learning":[94],"provided":[96],"focus":[98],"its":[100],"performance":[101],"online":[103],"mode.":[104],"Unlike":[105],"all":[106,139,155],"methods,":[108],"first":[111],"version":[112,194],"of":[113,127,169,175,190,195],"algorithm,":[115],"there":[116],"no":[118],"need":[119],"for":[120,186],"user":[122,161,179],"specify":[124],"weights":[126,191],"The":[130],"user\u2019s":[131],"preferences":[132,141,157,174],"not":[134],"completely":[136],"definite,":[137],"weight":[140,167],"are":[142],"combined":[143],"together":[144],"as":[145],"generated":[152],"by":[153],"considering":[154],"these":[156],"at":[158],"once":[159],"model":[163],"uncertainty":[165],"changes":[168],"around":[171],"their":[172],"specified":[173],"If":[177],"only":[180],"wants":[181],"apply":[183],"specific":[188],"set":[189],"second":[193],"efficiently":[198],"accomplishes":[199],"that.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}