{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T21:10:55Z","timestamp":1777669855386,"version":"3.51.4"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0102401"],"award-info":[{"award-number":["2018AAA0102401"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073234"],"award-info":[{"award-number":["62073234"]}],"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":["62003236"],"award-info":[{"award-number":["62003236"]}],"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":["61873340"],"award-info":[{"award-number":["61873340"]}],"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":["62022060"],"award-info":[{"award-number":["62022060"]}],"id":[{"id":"10.13039\/501100001809","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":[[2023,10]]},"DOI":"10.1109\/tnnls.2022.3146976","type":"journal-article","created":{"date-parts":[[2022,2,14]],"date-time":"2022-02-14T23:00:01Z","timestamp":1644879601000},"page":"7900-7909","source":"Crossref","is-referenced-by-count":178,"title":["Game of Drones: Multi-UAV Pursuit-Evasion Game With Online Motion Planning by Deep Reinforcement Learning"],"prefix":"10.1109","volume":"34","author":[{"given":"Ruilong","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0734-6728","authenticated-orcid":false,"given":"Qun","family":"Zong","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5309-6147","authenticated-orcid":false,"given":"Xiuyun","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}]},{"given":"Liqian","family":"Dou","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1004-8350","authenticated-orcid":false,"given":"Bailing","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2823329"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref34","article-title":"Emergence of grounded compositional language in multi-agent populations","author":"mordatch","year":"2017","journal-title":"arXiv 1703 04908"},{"key":"ref15","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2017","journal-title":"arXiv 1705 08926"},{"key":"ref37","article-title":"Unity: A general platform for intelligent agents","author":"juliani","year":"2018","journal-title":"arXiv 1809 02627"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref36","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761110"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.03.012"},{"key":"ref11","article-title":"Learning unmanned aerial vehicle control for autonomous target following","author":"li","year":"2017","journal-title":"arXiv 1709 08233"},{"key":"ref33","article-title":"Finite-time dynamic allocation and control in multiagent coordination for target tracking","author":"zhao","year":"2020","journal-title":"IEEE Trans Cybern"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6631276"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3004807"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2011.6161237"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2010.5717933"},{"key":"ref17","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"iqbal","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref39","article-title":"Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play StarCraft combat games","author":"peng","year":"2017","journal-title":"arXiv 1703 10069"},{"key":"ref16","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","author":"sukhbaatar","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1302409"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"key":"ref18","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 (NIPS)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2864373"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2900035"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967811"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5419"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2019.06.024"},{"key":"ref20","article-title":"Improving coordination in small-scale multi-agent deep reinforcement learning through memory-driven communication","author":"pesce","year":"2019","journal-title":"arXiv 1901 03887"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015015"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014213"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016079"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23919\/USNC\/URSI49741.2020.9321625"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZ-IEEE.2016.7737744"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2971780"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2923214"},{"key":"ref4","first-page":"117","article-title":"Particle swarm optimization of potential fields for obstacle avoidance","author":"palm","year":"2013","journal-title":"Proc Recent Adv Robot Mech"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2645516"},{"key":"ref6","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/70.163777"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV.2006.345353"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10273172\/09712866.pdf?arnumber=9712866","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T18:19:01Z","timestamp":1698085141000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9712866\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":45,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3146976","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}