{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T18:33:51Z","timestamp":1787164431966,"version":"build-2736575974"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51809246"],"award-info":[{"award-number":["51809246"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014761","name":"Natural Science Foundation of Qingdao Municipality","doi-asserted-by":"publisher","award":["23-2-1-153-zyyd-jch"],"award-info":[{"award-number":["23-2-1-153-zyyd-jch"]}],"id":[{"id":"10.13039\/501100014761","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Taishan Scholars Program","award":["tsqn202408072"],"award-info":[{"award-number":["tsqn202408072"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/lra.2025.3550743","type":"journal-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:48:04Z","timestamp":1741787284000},"page":"4356-4363","source":"Crossref","is-referenced-by-count":26,"title":["Multi-Agent Generative Adversarial Interactive Self-Imitation Learning for AUV Formation Control and Obstacle Avoidance"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9490-307X","authenticated-orcid":false,"given":"Zheng","family":"Fang","sequence":"first","affiliation":[{"name":"College of Electronic Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianhao","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tian","family":"Shen","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Jiang","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1728-5711","authenticated-orcid":false,"given":"Guangliang","family":"Li","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JOE.2013.2278891"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2021.109355"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2012.11.009"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2970433"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561188"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.apor.2022.103326"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2022.111453"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.05.016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1810959.1810981"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.06.006"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2022.112182"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/s22218562"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3162850"},{"key":"ref16","article-title":"Multiagent reinforcement learning for multi-robot systems: A survey","author":"Gu","year":"2004"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"key":"ref20","first-page":"661","article-title":"Efficient reductions for imitation learning","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist. Workshop Conf. Proc.","author":"Ross","year":"2010"},{"key":"ref21","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ng","year":"2000"},{"key":"ref22","first-page":"2760","article-title":"Model-free imitation learning with policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ho","year":"2016"},{"key":"ref23","first-page":"4565","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.apor.2023.103620"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2022.111971"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2019.2912447"},{"key":"ref27","first-page":"4300","article-title":"Deep reinforcement learning from human preferences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Christiano","year":"2017"},{"key":"ref28","first-page":"7472","article-title":"Multi-agent generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song","year":"2018"},{"key":"ref29","article-title":"Generative adversarial self-imitation learning","author":"Guo","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2943253"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7040156"},{"key":"ref34","article-title":"Is independent learning all you need in the starcraft multi-agent challenge?","author":"De Witt","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS.2018.8624183"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/OCEANS.2016.7761080"},{"key":"ref37","article-title":"Accelerating reinforcement learning of robotic manipulations via feedback from large language models","volume-title":"Proc. Conf. Robot Learn. Workshop","author":"Chu","year":"2023"},{"key":"ref38","article-title":"Safe RLHF: Safe reinforcement learning from human feedback","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Dai","year":"2024"},{"key":"ref39","first-page":"51303","article-title":"Probabilistic constrained reinforcement learning with formal interpretability","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Wang","year":"2024"},{"key":"ref40","first-page":"11480","article-title":"Crpo: A new approach for safe reinforcement learning with convergence guarantee","volume-title":"Proc. 38 th Int. Conf. Mach. Learn.","author":"Xu","year":"2021"},{"key":"ref41","article-title":"On a formal model of safe and scalable self-driving cars","author":"Shalev-Shwartz","year":"2018"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10935293\/10924397.pdf?arnumber=10924397","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T22:54:31Z","timestamp":1743029671000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10924397\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":41,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3550743","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}