{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T14:03:46Z","timestamp":1781618626867,"version":"3.54.5"},"reference-count":19,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72171126"],"award-info":[{"award-number":["72171126"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015973","name":"Systems Science Plus Joint Research Program of Qingdao University","doi-asserted-by":"publisher","award":["XT2024301"],"award-info":[{"award-number":["XT2024301"]}],"id":[{"id":"10.13039\/501100015973","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3655347","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T20:55:44Z","timestamp":1768856144000},"page":"9917-9934","source":"Crossref","is-referenced-by-count":2,"title":["Deep Reinforcement Learning-Based Pursuit\u2013Evasion Strategy for USVs in Complex Multi-Obstacle Environments"],"prefix":"10.1109","volume":"14","author":[{"given":"Jian","family":"Liu","sequence":"first","affiliation":[{"name":"Naval Submarine Academy, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, Qingdao University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2243-4136","authenticated-orcid":false,"given":"Hongwei","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, Qingdao University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Differential Games: A Mathematical Theory With Applications To Warfare and Pursuit, Optimization and Control","author":"Isaacs","year":"1965"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147205"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2017.08.2366"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s13235-019-00304-4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2025.3632473"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3520328"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/CCC55666.2022.9902778"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2023.115649"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.06.031"},{"key":"ref10","article-title":"A survey of progress on cooperative multi-agent reinforcement learning in open environment","author":"Yuan","year":"2023","journal-title":"arXiv:2312.01058"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.003"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3146976"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014213"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2023.114016"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124388"},{"key":"ref17","article-title":"Global path planning algorithm for multi-task amphibious unmanned surface vehicles based on double DQN","author":"Zhang","year":"2022","journal-title":"Ocean Eng."},{"key":"ref18","article-title":"Distributed pursuit-evasion game of finite-perception USV swarm based on multi-agent proximal policy optimization","author":"Chen","year":"2024","journal-title":"IEEE Trans. Syst., Man, Cybern."},{"key":"ref19","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Haarnoja"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11357903.pdf?arnumber=11357903","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T06:01:26Z","timestamp":1769493686000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11357903\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3655347","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}