{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T05:47:06Z","timestamp":1781243226566,"version":"3.54.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Open Project of the National Key Laboratory of Air-Based Information Perception and Fusion","award":["202437"],"award-info":[{"award-number":["202437"]}]},{"DOI":"10.13039\/501100004750","name":"Aeronautical Science Foundation of China","doi-asserted-by":"publisher","award":["20220001057001"],"award-info":[{"award-number":["20220001057001"]}],"id":[{"id":"10.13039\/501100004750","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004750","name":"Aeronautical Science Foundation of China","doi-asserted-by":"publisher","award":["20240001057002"],"award-info":[{"award-number":["20240001057002"]}],"id":[{"id":"10.13039\/501100004750","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tnnls.2025.3566548","type":"journal-article","created":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T13:45:21Z","timestamp":1747403121000},"page":"17034-17046","source":"Crossref","is-referenced-by-count":3,"title":["A Policy-Guided Reinforcement Learning Method for Encirclement Control in Multiobstacle Environment"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6149-3382","authenticated-orcid":false,"given":"Fandi","family":"Gou","sequence":"first","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haikuo","family":"Du","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6328-2788","authenticated-orcid":false,"given":"Chenyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1783-2984","authenticated-orcid":false,"given":"Yunze","family":"Cai","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2360368"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3004893"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3146976"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3182\/20140824-6-ZA-1003.00890"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2023.114016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICIA.2007.4295756"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/M-RA.2007.914932"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2628161"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2010.08.006"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2022.112742"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2024.3354890"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2022.3210291"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2023.3257364"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2015.2411632"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561054"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-019-01106-x"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812151"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207248"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.06.031"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068952"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1023\/B:AURO.0000033970.96785.f2"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2024.3469032"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3112572"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2023.3301511"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2002.1023918"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3241337"},{"key":"ref29","first-page":"34556","article-title":"Jump-start reinforcement learning","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Uchendu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abm6074"},{"key":"ref31","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative, multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Yu"},{"key":"ref32","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Lowe"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3069908"},{"issue":"1","key":"ref34","first-page":"1","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"Narvekar","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/671"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3201705"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2958548"},{"key":"ref38","article-title":"Is independent learning all you need in the StarCraft multi-agent challenge?","author":"Schroeder de Witt","year":"2020","journal-title":"arXiv:2011.09533"},{"key":"ref39","first-page":"16509","article-title":"Multi-agent reinforcement learning is a sequence modeling problem","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Wen"},{"key":"ref40","first-page":"1","article-title":"Heterogeneous-agent reinforcement learning","volume":"25","author":"Zhong","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref41","article-title":"Reducing overestimation bias in multi-agent domains using double centralized critics","author":"Ackermann","year":"2019","journal-title":"arXiv:1910.01465"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS.2018.8453470"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11151745\/11006133.pdf?arnumber=11006133","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T18:24:00Z","timestamp":1757096640000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11006133\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":42,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3566548","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}