{"id":"https://openalex.org/W4412444832","doi":"https://doi.org/10.1109/tase.2025.3589271","title":"Preference-Based Multi-Objective Reinforcement Learning","display_name":"Preference-Based Multi-Objective Reinforcement Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412444832","doi":"https://doi.org/10.1109/tase.2025.3589271"},"language":"en","primary_location":{"id":"doi:10.1109/tase.2025.3589271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3589271","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.14066","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014299354","display_name":"Ni Mu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ni Mu","raw_affiliation_strings":["Department of Automation, Center for Intelligent and Networked Systems (CFINS), Beijing National Research Center for Information Science and Technology, and Beijing Key Laboratory of Embodied Intelligence Systems, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-7793-0953","affiliations":[{"raw_affiliation_string":"Department of Automation, Center for Intelligent and Networked Systems (CFINS), Beijing National Research Center for Information Science and Technology, and Beijing Key Laboratory of Embodied Intelligence Systems, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yao Luan","orcid":"https://orcid.org/0009-0002-1548-432X"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Luan","raw_affiliation_strings":["Department of Automation, Center for Intelligent and Networked Systems (CFINS), Beijing National Research Center for Information Science and Technology, and Beijing Key Laboratory of Embodied Intelligence Systems, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-1548-432X","affiliations":[{"raw_affiliation_string":"Department of Automation, Center for Intelligent and Networked Systems (CFINS), Beijing National Research Center for Information Science and Technology, and Beijing Key Laboratory of Embodied Intelligence Systems, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044965133","display_name":"Qing\u2010Shan Jia","orcid":"https://orcid.org/0000-0002-4683-7215"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing-Shan Jia","raw_affiliation_strings":["Department of Automation, Center for Intelligent and Networked Systems (CFINS), Beijing National Research Center for Information Science and Technology, and Beijing Key Laboratory of Embodied Intelligence Systems, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4683-7215","affiliations":[{"raw_affiliation_string":"Department of Automation, Center for Intelligent and Networked Systems (CFINS), Beijing National Research Center for Information Science and Technology, and Beijing Key Laboratory of Embodied Intelligence Systems, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210094879"],"apc_list":null,"apc_paid":null,"fwci":5.0976,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.95561079,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"22","issue":null,"first_page":"18737","last_page":"18749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12546","display_name":"Smart Parking Systems Research","score":0.3831000030040741,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12546","display_name":"Smart Parking Systems Research","score":0.3831000030040741,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.3702999949455261,"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":0.6699416041374207},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5410948395729065},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5189083218574524},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.4387196898460388},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4201415777206421},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.30486440658569336},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.1358833611011505},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.10210064053535461},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.09814098477363586}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6699416041374207},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5410948395729065},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5189083218574524},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.4387196898460388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4201415777206421},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.30486440658569336},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.1358833611011505},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.10210064053535461},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.09814098477363586}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tase.2025.3589271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3589271","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2507.14066","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.14066","pdf_url":"https://arxiv.org/pdf/2507.14066","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.14066","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.14066","pdf_url":"https://arxiv.org/pdf/2507.14066","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G184828240","display_name":null,"funder_award_id":"62192751","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2671578558","display_name":null,"funder_award_id":"2022YFA1004600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5492808859","display_name":null,"funder_award_id":"62125304","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8836869627","display_name":null,"funder_award_id":"BNR2024TD03003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1588513474","https://openalex.org/W1965455100","https://openalex.org/W2012612381","https://openalex.org/W2056877664","https://openalex.org/W2141481921","https://openalex.org/W2171122588","https://openalex.org/W2521826931","https://openalex.org/W2610279045","https://openalex.org/W2763110165","https://openalex.org/W2766447205","https://openalex.org/W2902922568","https://openalex.org/W3133533407","https://openalex.org/W4214717370","https://openalex.org/W4287266177","https://openalex.org/W4380371586","https://openalex.org/W4385783819","https://openalex.org/W4386922880","https://openalex.org/W4389002566","https://openalex.org/W4389719636","https://openalex.org/W4392941164","https://openalex.org/W4392942009","https://openalex.org/W4403676845","https://openalex.org/W4407466734","https://openalex.org/W4409494151","https://openalex.org/W6637967152","https://openalex.org/W6677285668","https://openalex.org/W6739585900","https://openalex.org/W6753960536","https://openalex.org/W6756303580","https://openalex.org/W6756714161","https://openalex.org/W6766952794","https://openalex.org/W6779795787","https://openalex.org/W6780559895","https://openalex.org/W6782465632","https://openalex.org/W6782628559","https://openalex.org/W6796168157","https://openalex.org/W6799431981","https://openalex.org/W6803476162","https://openalex.org/W6810044100","https://openalex.org/W6810121075","https://openalex.org/W6847148345","https://openalex.org/W6847353123","https://openalex.org/W6849884502","https://openalex.org/W6852418670","https://openalex.org/W6852909087","https://openalex.org/W6860635184","https://openalex.org/W6864687407","https://openalex.org/W6866896568","https://openalex.org/W6873345306","https://openalex.org/W6947882152"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Multi-objective":[0],"reinforcement":[1],"learning":[2],"(MORL)":[3],"is":[4,114],"a":[5,92,128,138],"structured":[6],"approach":[7],"for":[8,28,50,162],"optimizing":[9,110],"tasks":[10],"with":[11,98],"multiple":[12],"objectives.":[13],"However,":[14],"it":[15],"often":[16],"relies":[17],"on":[18,137],"pre-defined":[19],"reward":[20,52,94,112,156],"functions,":[21],"which":[22,60,151],"can":[23,38,75],"be":[24],"hard":[25],"to":[26,35,107,116],"design":[27],"balancing":[29],"conflicting":[30],"goals":[31],"and":[32,43,132],"may":[33],"lead":[34],"oversimplification.":[36],"Preferences":[37],"serve":[39],"as":[40],"more":[41],"flexible":[42],"intuitive":[44],"decision-making":[45],"guidance,":[46],"eliminating":[47],"the":[48,62,67,79,99,118,148,153],"need":[49],"complicated":[51],"design.":[53],"This":[54,158],"paper":[55],"introduces":[56],"preference-based":[57],"MORL":[58,68],"(Pb-MORL),":[59],"formalizes":[61],"integration":[63],"of":[64],"preferences":[65,74],"into":[66],"framework.":[69],"We":[70,102],"theoretically":[71],"prove":[72],"that":[73,96,109,142],"derive":[76],"policies":[77],"across":[78],"entire":[80],"Pareto":[81,119],"frontier.":[82],"To":[83],"guide":[84],"policy":[85],"optimization":[86],"using":[87],"preferences,":[88],"our":[89,143],"method":[90,144],"constructs":[91],"multi-objective":[93,126],"model":[95,113],"aligns":[97],"given":[100],"preferences.":[101],"further":[103],"provide":[104],"theoretical":[105],"proof":[106],"show":[108,141],"this":[111],"equivalent":[115],"training":[117],"optimal":[120],"policy.":[121],"Extensive":[122],"experiments":[123],"in":[124,165],"benchmark":[125],"tasks,":[127],"multi-energy":[129],"management":[130],"task,":[131],"an":[133],"autonomous":[134],"driving":[135],"task":[136],"multi-line":[139],"highway":[140],"performs":[145],"competitively,":[146],"surpassing":[147],"oracle":[149],"method,":[150],"uses":[152],"ground":[154],"truth":[155],"function.":[157],"highlights":[159],"its":[160],"potential":[161],"practical":[163],"applications":[164],"complex":[166],"real-world":[167],"systems.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}