{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T14:49:57Z","timestamp":1780757397667,"version":"3.54.1"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1913202"],"award-info":[{"award-number":["U1913202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1813205"],"award-info":[{"award-number":["U1813205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010083","name":"Hunan Provincial Innovation Foundation for Postgraduate","doi-asserted-by":"publisher","award":["CX2018B010"],"award-info":[{"award-number":["CX2018B010"]}],"id":[{"id":"10.13039\/501100010083","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3016951","type":"journal-article","created":{"date-parts":[[2020,8,17]],"date-time":"2020-08-17T21:30:27Z","timestamp":1597699827000},"page":"150397-150406","source":"Crossref","is-referenced-by-count":71,"title":["Multi-Robot Flocking Control Based on Deep Reinforcement Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2440-5331","authenticated-orcid":false,"given":"Pengming","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0361-6620","authenticated-orcid":false,"given":"Weijia","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junchong","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiwen","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6375-581X","authenticated-orcid":false,"given":"Huimin","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2509646"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2015.335"},{"key":"ref31","article-title":"A reinforcement learning scheme of adaptive flocking behavior","author":"tomimasu","year":"2005","journal-title":"Proc Int Symp Artificial Life and Robotics (AROB)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SICE.2006.315087"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA.2018.8444355"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.79.052102"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-017-3644-5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS.2014.6842259"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8431870"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2010897"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref16","article-title":"Off-policy actor-critic","author":"degris","year":"2012","journal-title":"arXiv 1205 4839"},{"key":"ref17","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref19","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2943253"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICInfA.2017.8078889"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC45663.2020.9120592"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915602321"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-016-9579-8"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-019-01106-x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/00207721.2013.795632"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/37401.37406"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2360368"},{"key":"ref2","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv 1511 05952"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.75.1226"},{"key":"ref1","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-019-01081-3"},{"key":"ref22","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","author":"sukhbaatar","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2015","journal-title":"arXiv 1509 06461 [cs]"},{"key":"ref23","article-title":"Lenient multi-agent deep reinforcement learning","author":"palmer","year":"2017","journal-title":"arXiv 1707 04402"},{"key":"ref26","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2020","journal-title":"arXiv 2003 08839"},{"key":"ref25","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2017","journal-title":"arXiv 1705 08926"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09169650.pdf?arnumber=9169650","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:13Z","timestamp":1639770913000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9169650\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3016951","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}