{"id":"https://openalex.org/W4416749501","doi":"https://doi.org/10.1109/iros60139.2025.11246039","title":"Human Implicit Preference-Based Policy Fine-tuning for Multi-Agent Reinforcement Learning in USV Swarm","display_name":"Human Implicit Preference-Based Policy Fine-tuning for Multi-Agent Reinforcement Learning in USV Swarm","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749501","doi":"https://doi.org/10.1109/iros60139.2025.11246039"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101826732","display_name":"Hyeon-Jun Kim","orcid":"https://orcid.org/0000-0002-6290-2611"},"institutions":[{"id":"https://openalex.org/I184908088","display_name":"Korea Military Academy","ror":"https://ror.org/024ctqw02","country_code":"KR","type":"education","lineage":["https://openalex.org/I184908088"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeonjun Kim","raw_affiliation_strings":["Korea Military Academy (KMA),Seoul,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Military Academy (KMA),Seoul,Korea","institution_ids":["https://openalex.org/I184908088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564799","display_name":"Kanghoon Lee","orcid":"https://orcid.org/0000-0003-0749-6398"},"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":"Kanghoon Lee","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667214","display_name":"Junho Park","orcid":"https://orcid.org/0009-0002-5421-594X"},"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":"Junho Park","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357070","display_name":"Jiachen Li","orcid":"https://orcid.org/0000-0002-4883-697X"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiachen Li","raw_affiliation_strings":["University of California,Riverside,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Riverside,CA,USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023509025","display_name":"Jinkyoo Park","orcid":"https://orcid.org/0000-0003-2620-1479"},"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":"Jinkyoo Park","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18653","last_page":"18659"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6672000288963318,"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":0.6672000288963318,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.03359999880194664,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11622","display_name":"Maritime Navigation and Safety","score":0.031700000166893005,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7858999967575073},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.6406000256538391},{"id":"https://openalex.org/keywords/swarm-behaviour","display_name":"Swarm behaviour","score":0.6057000160217285},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.48989999294281006},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4796999990940094},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.44350001215934753}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7858999967575073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.711899995803833},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.6406000256538391},{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.6057000160217285},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.48989999294281006},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4796999990940094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4713999927043915},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.44350001215934753},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29760000109672546},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2669000029563904}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W587026357","https://openalex.org/W1967398213","https://openalex.org/W1972566002","https://openalex.org/W1973564335","https://openalex.org/W2125298858","https://openalex.org/W2728420778","https://openalex.org/W2763110165","https://openalex.org/W2962764565","https://openalex.org/W2990747716","https://openalex.org/W3000232681","https://openalex.org/W3007565530","https://openalex.org/W3086606660","https://openalex.org/W3204431142","https://openalex.org/W3205373118","https://openalex.org/W3207864249","https://openalex.org/W3208617162","https://openalex.org/W4200219032","https://openalex.org/W4206742276","https://openalex.org/W4304614160","https://openalex.org/W4312583411","https://openalex.org/W4321763414","https://openalex.org/W4387010714","https://openalex.org/W4389666601","https://openalex.org/W4389667358","https://openalex.org/W4391559452","https://openalex.org/W4391768956","https://openalex.org/W4393148062","https://openalex.org/W4396910051","https://openalex.org/W4405429243","https://openalex.org/W4416033919"],"related_works":[],"abstract_inverted_index":{"Multi-Agent":[0],"Reinforcement":[1,61],"Learning":[2,62],"(MARL)":[3],"has":[4],"shown":[5],"promise":[6],"in":[7,26,129],"solving":[8],"complex":[9],"problems":[10],"involving":[11],"cooperation":[12],"and":[13,28,31,84,116,135],"competition":[14],"among":[15],"agents,":[16],"such":[17,110],"as":[18,111],"an":[19,75],"Unmanned":[20],"Surface":[21],"Vehicle":[22],"(USV)":[23],"swarm":[24,124],"used":[25],"search":[27],"rescue,":[29],"surveillance,":[30],"vessel":[32],"protection.":[33],"However,":[34],"aligning":[35],"system":[36,78],"behavior":[37],"with":[38,63],"user":[39],"preferences":[40],"is":[41],"challenging":[42],"due":[43],"to":[44,103],"the":[45,56,89],"difficulty":[46],"of":[47,91],"encoding":[48],"expert":[49],"intuition":[50],"into":[51,81],"reward":[52],"functions.":[53],"To":[54,87],"address":[55],"issue,":[57],"we":[58,95],"propose":[59],"a":[60,97],"Human":[64],"Feedback":[65,77],"(RLHF)":[66],"approach":[67,106],"for":[68],"MARL":[69],"that":[70],"resolves":[71],"credit-assignment":[72],"challenges":[73,90,128],"through":[74],"Agent-Level":[76],"categorizing":[79],"feedback":[80,108],"intra-agent,":[82],"inter-agent,":[83],"intra-team":[85],"types.":[86],"overcome":[88],"direct":[92],"human":[93],"feedback,":[94],"employ":[96],"Large":[98],"Language":[99],"Model":[100],"(LLM)":[101],"evaluator":[102],"validate":[104],"our":[105],"using":[107],"scenarios":[109],"region":[112],"constraints,":[113],"collision":[114],"avoidance,":[115],"task":[117],"allocation.":[118],"Our":[119],"method":[120],"effectively":[121],"refines":[122],"USV":[123],"policies,":[125],"addressing":[126],"key":[127],"multi-agent":[130],"systems":[131],"while":[132],"maintaining":[133],"fairness":[134],"performance":[136],"consistency.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}