{"id":"https://openalex.org/W4417470046","doi":"https://doi.org/10.1109/access.2025.3645778","title":"Dual Preference Learning for Multi-Agent Reinforcement Learning","display_name":"Dual Preference Learning for Multi-Agent Reinforcement Learning","publication_year":2025,"publication_date":"2025-12-18","ids":{"openalex":"https://openalex.org/W4417470046","doi":"https://doi.org/10.1109/access.2025.3645778"},"language":null,"primary_location":{"id":"doi:10.1109/access.2025.3645778","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3645778","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3645778","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073701805","display_name":"Sehyeok Kang","orcid":"https://orcid.org/0000-0002-1163-037X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sehyeok Kang","raw_affiliation_strings":["Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Seoul, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107167845","display_name":"Minu Kim","orcid":"https://orcid.org/0009-0002-3419-159X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minu Kim","raw_affiliation_strings":["Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Seoul, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016410893","display_name":"Jihwan Oh","orcid":"https://orcid.org/0000-0003-3274-4533"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jihwan Oh","raw_affiliation_strings":["Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Seoul, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091674853","display_name":"Se-Young Yun","orcid":"https://orcid.org/0000-0001-6675-5113"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Se-Young Yun","raw_affiliation_strings":["Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Seoul, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5073701805"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21746547,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"113","last_page":"130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8698999881744385,"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":0.8698999881744385,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.012799999676644802,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.004699999932199717,"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":0.8822000026702881},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.7461000084877014},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5212000012397766},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5058000087738037},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4611000120639801},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4578000009059906},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.43689998984336853},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.3978999853134155}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8822000026702881},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.7461000084877014},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7095000147819519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5649999976158142},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5212000012397766},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5058000087738037},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4611000120639801},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4578000009059906},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.43689998984336853},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4343000054359436},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.3840000033378601},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.36469998955726624},{"id":"https://openalex.org/C2778444522","wikidata":"https://www.wikidata.org/wiki/Q1081491","display_name":"Football","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.3400000035762787},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.3156999945640564},{"id":"https://openalex.org/C12298181","wikidata":"https://www.wikidata.org/wiki/Q7246814","display_name":"Proactive learning","level":5,"score":0.30559998750686646},{"id":"https://openalex.org/C143661069","wikidata":"https://www.wikidata.org/wiki/Q670713","display_name":"Reward system","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C117035363","wikidata":"https://www.wikidata.org/wiki/Q3769299","display_name":"Human behavior","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/access.2025.3645778","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3645778","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3645778","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3645778","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2747213132","https://openalex.org/W2763110165","https://openalex.org/W2997502221","https://openalex.org/W3119264617","https://openalex.org/W3156295478","https://openalex.org/W4239181501","https://openalex.org/W4382239386","https://openalex.org/W4393148062","https://openalex.org/W4393160007"],"related_works":[],"abstract_inverted_index":{"Designing":[0],"effective":[1],"reward":[2,28,96],"functions":[3],"is":[4],"fundamental":[5],"challenging":[6],"in":[7,11,38,142,148],"reinforcement":[8,20],"learning,":[9],"especially":[10],"complex":[12],"multi-agent":[13,50,149],"systems":[14,51],"with":[15],"intricate":[16],"credit":[17,60],"assignment.":[18],"Preference-based":[19,70],"learning":[21,31,97],"(PbRL)":[22],"offers":[23],"an":[24],"alternative":[25],"to":[26,49,53,89,105],"manual":[27],"engineering":[29],"by":[30],"from":[32],"preferences.":[33],"However,":[34],"the":[35,117,124],"prevalent":[36],"approach":[37],"PbRL,":[39],"which":[40,75],"involves":[41],"pairwise":[42],"trajectory":[43],"comparisons,":[44],"encounters":[45],"difficulties":[46],"when":[47],"applied":[48],"due":[52],"exponentially":[54],"large":[55],"state-action":[56],"spaces":[57],"and":[58,92,116,129,145],"temporal":[59],"assignment":[61],"problem.":[62],"To":[63],"address":[64],"these":[65],"challenges,":[66],"we":[67],"introduce":[68],"Dual":[69],"Multi-Agent":[71,126],"Reinforcement":[72],"Learning":[73],"(DPM),":[74],"uniquely":[76],"employs":[77],"dual":[78,107],"preferences:":[79],"trajectory-level":[80],"and,":[81],"crucially,":[82],"transition-level":[83],"agent":[84],"contribution":[85],"comparisons.":[86],"This":[87],"allows":[88],"distinguish":[90],"cooperative":[91],"non-cooperative":[93],"actions,":[94],"enhancing":[95],"efficiency.":[98],"Furthermore,":[99],"DPM":[100,140],"leverages":[101],"Large":[102],"Language":[103],"Models":[104],"generate":[106],"preferences,":[108],"significantly":[109],"reducing":[110],"reliance":[111],"on":[112,123],"costly":[113],"human":[114,120],"feedback":[115],"potential":[118],"for":[119],"error.":[121],"Experiments":[122],"StarCraft":[125],"Challenge,":[127],"SMACv2,":[128],"Google":[130],"Research":[131],"Football":[132],"show":[133],"significant":[134],"performance":[135,147],"gains":[136],"over":[137],"baselines,":[138],"demonstrating":[139],"effectiveness":[141],"optimizing":[143],"rewards":[144],"improving":[146],"systems.":[150]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-18T00:00:00"}