{"id":"https://openalex.org/W1987725948","doi":"https://doi.org/10.1109/tsmc.2014.2358639","title":"Multiobjective Reinforcement Learning: A Comprehensive Overview","display_name":"Multiobjective Reinforcement Learning: A Comprehensive Overview","publication_year":2014,"publication_date":"2014-10-08","ids":{"openalex":"https://openalex.org/W1987725948","doi":"https://doi.org/10.1109/tsmc.2014.2358639","mag":"1987725948"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2014.2358639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2014.2358639","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics: Systems","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/A5100623407","display_name":"Chunming Liu","orcid":"https://orcid.org/0000-0002-5440-4938"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunming Liu","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","College of Mechatronics and Automation; National University of Defense Technology; Changsha China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Mechatronics and Automation; National University of Defense Technology; Changsha China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053112608","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-3238-745X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["Institute of Unmanned Systems, College of Mechatronics and Automation, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Unmanned Systems, College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071074935","display_name":"Dewen Hu","orcid":"https://orcid.org/0000-0001-7357-0053"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dewen Hu","raw_affiliation_strings":["Department of Automatic Control, National University of Defense Technology, Changsha, China","Department of Automatic ControlCollege of Mechatronics and Automation, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automatic Control, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Department of Automatic ControlCollege of Mechatronics and Automation, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":14.9105,"has_fulltext":false,"cited_by_count":359,"citation_normalized_percentile":{"value":0.99013314,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"45","issue":"3","first_page":"385","last_page":"398"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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":0.998199999332428,"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":0.9914000034332275,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9889000058174133,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8817410469055176},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.652972400188446},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4894958734512329},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44194912910461426},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4136573374271393},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.3968433439731598},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3704965114593506},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12617576122283936}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8817410469055176},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.652972400188446},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4894958734512329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44194912910461426},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4136573374271393},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3968433439731598},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3704965114593506},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12617576122283936},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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":1,"locations":[{"id":"doi:10.1109/tsmc.2014.2358639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2014.2358639","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320342","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":137,"referenced_works":["https://openalex.org/W24785488","https://openalex.org/W32403112","https://openalex.org/W47799525","https://openalex.org/W72400652","https://openalex.org/W119236796","https://openalex.org/W153753672","https://openalex.org/W643078925","https://openalex.org/W950288201","https://openalex.org/W1480676279","https://openalex.org/W1513695137","https://openalex.org/W1540831149","https://openalex.org/W1543572792","https://openalex.org/W1549353711","https://openalex.org/W1557760016","https://openalex.org/W1574700590","https://openalex.org/W1585546214","https://openalex.org/W1633494854","https://openalex.org/W1854776945","https://openalex.org/W1875923360","https://openalex.org/W1964581121","https://openalex.org/W1968535060","https://openalex.org/W1976102653","https://openalex.org/W1982262386","https://openalex.org/W1995053973","https://openalex.org/W1998649829","https://openalex.org/W1999371911","https://openalex.org/W1999874108","https://openalex.org/W2001771035","https://openalex.org/W2005762133","https://openalex.org/W2010225880","https://openalex.org/W2010526786","https://openalex.org/W2012612381","https://openalex.org/W2014729048","https://openalex.org/W2016327843","https://openalex.org/W2016678909","https://openalex.org/W2017647470","https://openalex.org/W2020066883","https://openalex.org/W2022783922","https://openalex.org/W2029387675","https://openalex.org/W2031811237","https://openalex.org/W2033197828","https://openalex.org/W2034294515","https://openalex.org/W2041225042","https://openalex.org/W2041367235","https://openalex.org/W2044332520","https://openalex.org/W2044922360","https://openalex.org/W2045276965","https://openalex.org/W2050838777","https://openalex.org/W2052078109","https://openalex.org/W2060882019","https://openalex.org/W2061562262","https://openalex.org/W2081455098","https://openalex.org/W2084261982","https://openalex.org/W2084854855","https://openalex.org/W2086608109","https://openalex.org/W2089561656","https://openalex.org/W2093083665","https://openalex.org/W2097031964","https://openalex.org/W2097746659","https://openalex.org/W2097780422","https://openalex.org/W2098907614","https://openalex.org/W2099618002","https://openalex.org/W2100677568","https://openalex.org/W2101391429","https://openalex.org/W2102660061","https://openalex.org/W2103626435","https://openalex.org/W2104602264","https://openalex.org/W2107219912","https://openalex.org/W2107726111","https://openalex.org/W2108511252","https://openalex.org/W2113815608","https://openalex.org/W2114672365","https://openalex.org/W2116001481","https://openalex.org/W2116769723","https://openalex.org/W2117428849","https://openalex.org/W2117626647","https://openalex.org/W2118556122","https://openalex.org/W2119080972","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2132351269","https://openalex.org/W2132482672","https://openalex.org/W2134882417","https://openalex.org/W2141481921","https://openalex.org/W2143381319","https://openalex.org/W2145482038","https://openalex.org/W2147995533","https://openalex.org/W2150339816","https://openalex.org/W2151726636","https://openalex.org/W2152213878","https://openalex.org/W2152809978","https://openalex.org/W2156067405","https://openalex.org/W2158548602","https://openalex.org/W2159306970","https://openalex.org/W2161795906","https://openalex.org/W2165131254","https://openalex.org/W2169673701","https://openalex.org/W2332106906","https://openalex.org/W2332784914","https://openalex.org/W2387363679","https://openalex.org/W2477937608","https://openalex.org/W2546352153","https://openalex.org/W2759526291","https://openalex.org/W3027095131","https://openalex.org/W3041202696","https://openalex.org/W3103262232","https://openalex.org/W4214717370","https://openalex.org/W4249441547","https://openalex.org/W6601003894","https://openalex.org/W6604948569","https://openalex.org/W6618246250","https://openalex.org/W6624893745","https://openalex.org/W6628735244","https://openalex.org/W6632292508","https://openalex.org/W6632316456","https://openalex.org/W6633217410","https://openalex.org/W6634919779","https://openalex.org/W6639372798","https://openalex.org/W6653228414","https://openalex.org/W6654271366","https://openalex.org/W6660998847","https://openalex.org/W6671676952","https://openalex.org/W6671821248","https://openalex.org/W6672734911","https://openalex.org/W6673579136","https://openalex.org/W6674628981","https://openalex.org/W6675811377","https://openalex.org/W6677435986","https://openalex.org/W6677477198","https://openalex.org/W6677504650","https://openalex.org/W6682455769","https://openalex.org/W6682753738","https://openalex.org/W6683443546","https://openalex.org/W6683841269","https://openalex.org/W6744321307","https://openalex.org/W6992881652","https://openalex.org/W6993026462"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2089013912","https://openalex.org/W2076061571","https://openalex.org/W1987513656","https://openalex.org/W2145821588"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,52],"(RL)":[2],"is":[3,66],"a":[4,69],"powerful":[5],"paradigm":[6],"for":[7],"sequential":[8],"decision-making":[9],"under":[10],"uncertainties,":[11],"and":[12,38,79,93,107,120,126],"most":[13],"RL":[14],"algorithms":[15],"aim":[16,62],"to":[17,67],"maximize":[18],"some":[19,94],"numerical":[20],"value":[21],"which":[22,114],"represents":[23],"only":[24],"one":[25],"long-term":[26,30],"objective.":[27],"However,":[28],"multiple":[29,58],"objectives":[31],"are":[32,57,84,100,111,132],"exhibited":[33],"in":[34,48],"many":[35],"real-world":[36],"decision":[37],"control":[39],"systems,":[40],"so":[41],"recently":[42],"there":[43,56],"has":[44],"been":[45],"growing":[46],"interest":[47],"solving":[49],"multiobjective":[50,116],"reinforcement":[51],"(MORL)":[53],"problems":[54,128],"where":[55],"conflicting":[59],"objectives.":[60],"The":[61,74,103],"of":[63,72,82,97,129],"this":[64],"paper":[65],"present":[68],"comprehensive":[70],"overview":[71],"MORL.":[73],"basic":[75],"architecture,":[76],"research":[77,99,110,124],"topics,":[78],"na\u00efve":[80],"solutions":[81],"MORL":[83,91,106,130],"introduced":[85],"at":[86],"first.":[87],"Then,":[88],"several":[89],"representative":[90],"approaches":[92],"important":[95],"directions":[96],"recent":[98],"comprehensively":[101],"reviewed.":[102],"relationships":[104],"between":[105],"other":[108],"related":[109],"also":[112],"discussed,":[113],"include":[115],"optimization,":[117],"hierarchical":[118],"RL,":[119],"multiagent":[121],"RL.":[122],"Moreover,":[123],"challenges":[125],"open":[127],"techniques":[131],"suggested.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":43},{"year":2023,"cited_by_count":42},{"year":2022,"cited_by_count":48},{"year":2021,"cited_by_count":54},{"year":2020,"cited_by_count":43},{"year":2019,"cited_by_count":37},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":22},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}