{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T15:32:13Z","timestamp":1775662333927,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10341975","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"2232-2239","source":"Crossref","is-referenced-by-count":7,"title":["Large Scale Pursuit-Evasion Under Collision Avoidance Using Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Helei","family":"Yang","sequence":"first","affiliation":[{"name":"The Institute of Cyber-Systems and Control, Zhejiang University,Hangzhou,China,310027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Ge","sequence":"additional","affiliation":[{"name":"The Institute of Cyber-Systems and Control, Zhejiang University,Hangzhou,China,310027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjie","family":"Cao","sequence":"additional","affiliation":[{"name":"The Institute of Cyber-Systems and Control, Zhejiang University,Hangzhou,China,310027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Yang","sequence":"additional","affiliation":[{"name":"The Institute of Cyber-Systems and Control, Zhejiang University,Hangzhou,China,310027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Liu","sequence":"additional","affiliation":[{"name":"The Institute of Cyber-Systems and Control, Zhejiang University,Hangzhou,China,310027"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2015.11.018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2514\/1.G000461"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(02)00273-X"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00138"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS.2018.8453470"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.05.007"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.2514\/1.G002125"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068952"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.06.031"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5220\/0008971502260233"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.23919\/FUSION49465.2021.9627024"},{"key":"ref12","article-title":"Is independent learning all you need in the starcraft multi-agent challenge?","author":"de Witt","year":"2020","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Emergent tool use from multi-agent autocurricula","author":"Baker","year":"2019","journal-title":"arXiv preprint"},{"key":"ref14","volume-title":"Differential games","author":"Friedman","year":"2013"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/acc.2013.6580676"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF01078897"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0070400"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2009.2035737"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-017-1155-7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.beproc.2011.09.006"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2575008"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cnsns.2022.106386"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TRA.2002.804040"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463196"},{"key":"ref25","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International conference on machine learning. PMLR","author":"Fujimoto"},{"key":"ref26","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.01.141"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11537-007-0657-8"},{"issue":"54","key":"ref29","first-page":"1","article-title":"Deep reinforcement learning for swarm systems","volume":"20","author":"Huttenrauch","year":"2019","journal-title":"Journal of Machine Learning Research"},{"key":"ref30","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International conference on machine learning. PMLR","author":"Schulman"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-32-9682-4_69"},{"key":"ref32","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3050338"},{"key":"ref36","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref37","article-title":"Deep sets","volume":"30","author":"Zaheer","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487258"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10341975.pdf?arnumber=10341975","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T01:22:46Z","timestamp":1705022566000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341975\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341975","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}