{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,26]],"date-time":"2026-07-26T06:25:28Z","timestamp":1785047128015,"version":"3.55.0"},"reference-count":41,"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":["91216304"],"award-info":[{"award-number":["91216304"]}],"id":[{"id":"10.13039\/501100001809","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.2020.2971780","type":"journal-article","created":{"date-parts":[[2020,2,5]],"date-time":"2020-02-05T23:34:36Z","timestamp":1580945676000},"page":"29064-29074","source":"Crossref","is-referenced-by-count":158,"title":["Path Planning for UAV Ground Target Tracking via Deep Reinforcement Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7354-2116","authenticated-orcid":false,"given":"Bohao","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3234-0117","authenticated-orcid":false,"given":"Yunjie","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"The uncertainty bellman equation and exploration","author":"o\u2019donoghue","year":"2017","journal-title":"arXiv 1709 05380"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2016.7524384"},{"key":"ref33","article-title":"Dopamine: A research framework for deep reinforcement learning","author":"castro","year":"2018","journal-title":"arXiv 1812 06110"},{"key":"ref32","article-title":"The reactor: A fast and sample-efficient actor-critic agent for reinforcement learning","author":"gruslys","year":"2017","journal-title":"arXiv 1704 04651"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2933002"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1080\/00207721.2014.929191"},{"key":"ref37","article-title":"Recurrent deterministic policy gradient method for bipedal locomotion on rough terrain challenge","author":"song","year":"2017","journal-title":"arXiv 1710 02896"},{"key":"ref36","article-title":"The emergence of number and syntax units in LSTM language models","author":"lakretz","year":"2019","journal-title":"arXiv 1903 07435"},{"key":"ref35","article-title":"Neural network unit that performs concurrent LSTM cell calculations","author":"henry","year":"2017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"ref10","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":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2019.10.035"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.01.054"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-013-9901-z"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/ChiCC.2017.8027884"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAS.2018.8443226"},{"key":"ref15","article-title":"Efficient entropy for policy gradient with multidimensional action space","author":"zhang","year":"2018","journal-title":"arXiv 1806 00589"},{"key":"ref16","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","article-title":"Q-Prop: Sample-efficient policy gradient with an off-policy critic","author":"gu","year":"2016","journal-title":"arXiv 1611 02247"},{"key":"ref18","first-page":"1","article-title":"Global convergence of policy gradient methods for linearized control problems","author":"fazel","year":"2018","journal-title":"Proc ICLR"},{"key":"ref19","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"arXiv 1802 09477"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683875"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2018.2876738"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2010.5717933"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2019.1662947"},{"key":"ref5","article-title":"Automatic navigation using deep reinforcement learning","author":"balakrishnan","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2935255"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3182\/20080706-5-KR-1001.01446"},{"key":"ref9","first-page":"2613","article-title":"Double Q-learning","author":"hasselt","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2885776"},{"key":"ref20","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":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WCICA.2016.7578765"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2018.8650160"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890773"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01138"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-5739-5"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2905649"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/08984371.pdf?arnumber=8984371","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:51:26Z","timestamp":1639770686000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8984371\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2971780","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}