{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T06:33:48Z","timestamp":1770532428989,"version":"3.49.0"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246039","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"18653-18659","source":"Crossref","is-referenced-by-count":1,"title":["Human Implicit Preference-Based Policy Fine-tuning for Multi-Agent Reinforcement Learning in USV Swarm"],"prefix":"10.1109","author":[{"given":"Hyeonjun","family":"Kim","sequence":"first","affiliation":[{"name":"Korea Military Academy (KMA),Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kanghoon","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junho","family":"Park","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiachen","family":"Li","sequence":"additional","affiliation":[{"name":"University of California,Riverside,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinkyoo","family":"Park","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref2","article-title":"Multi-agent dynamic relational reasoning for social robot navigation","author":"Li","year":"2024"},{"key":"ref3","article-title":"Towards generalizable safety in crowd navigation via conformal uncertainty handling","author":"Yao","year":"2024"},{"key":"ref4","article-title":"Robust offline imitation learning from diverse auxiliary data","author":"Ghosh","year":"2025","journal-title":"Transactions on Machine Learning Research"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562006"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564518"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01579"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342038"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3400937"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3518087"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-47148-x"},{"key":"ref12","first-page":"7204","article-title":"Trajectory diversity for zero-shot coordination","volume-title":"International conference on machine learning","author":"Lupu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636193"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10422469"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982277"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636053"},{"key":"ref17","article-title":"The effects of reward misspecification: Mapping and mitigating misaligned models","author":"Pan","year":"2022"},{"key":"ref18","first-page":"9460","article-title":"Defining and characterizing reward gaming","volume":"35","author":"Skalse","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.17226\/6018"},{"key":"ref20","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Learning a universal human prior for dexterous manipulation from human preference","author":"Ding","year":"2023"},{"key":"ref22","article-title":"Preference vlm: Leveraging vlms for scalable preference-based reinforcement learning","author":"Ghosh","year":"2025"},{"key":"ref23","first-page":"3008","article-title":"Learning to summarize with human feedback","volume":"33","author":"Stiennon","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","article-title":"Webgpt: Browser-assisted question-answering with human feedback","author":"Nakano","year":"2021"},{"key":"ref25","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.1158"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2974047"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JOE.2023.3281630"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1115\/1.4038974"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2011.2174376"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.06.066"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2020.107704"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342389"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.1526"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-014-9409-9"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.23919\/ICCAS52745.2021.9649839"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.dt.2022.09.014"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3363044"},{"key":"ref39","article-title":"Multi-agent reinforcement learning from human feedback: Data coverage and algorithmic techniques","author":"Zhang","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2023.114016"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282477"},{"key":"ref42","article-title":"Inverse reward design","volume":"30","author":"Hadfield-Menell","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref43","first-page":"21406","article-title":"Avoiding side effects in complex environments","volume":"33","author":"Turner","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref44","article-title":"Reward learning from human preferences and demonstrations in atari","author":"Ibarz","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref45","article-title":"Pebble: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","author":"Lee","year":"2021"},{"key":"ref46","article-title":"Meta-reward-net: Implicitly differentiable reward learning for preference-based reinforcement learning","author":"Liu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref47","article-title":"Few-shot preference learning for human-in-the-loop rl","volume-title":"Conference on Robot Learning","author":"Hejna"},{"key":"ref48","article-title":"Rudder: Return decomposition for delayed rewards","volume":"32","author":"Arjona-Medina","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref49","article-title":"Preference transformer: Modeling human preferences using transformers for rl","author":"Kim","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29666"},{"key":"ref51","article-title":"Dynamic programming for partially observable stochastic games","author":"Hansen","year":"2004","journal-title":"AAAI"},{"key":"ref52","article-title":"Relational inductive biases, deep learning, and graph networks","author":"Battaglia","year":"2018"},{"key":"ref53","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"ref55","article-title":"Is independent learning all you need in the starcraft multi-agent challenge?","author":"De Witt","year":"2020"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246039.pdf?arnumber=11246039","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:09:22Z","timestamp":1765519762000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246039\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246039","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}