{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T17:08:55Z","timestamp":1785517735533,"version":"3.56.0"},"reference-count":14,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,11]]},"DOI":"10.1109\/globalsip.2017.8309082","type":"proceedings-article","created":{"date-parts":[[2018,3,12]],"date-time":"2018-03-12T20:33:04Z","timestamp":1520886784000},"page":"858-862","source":"Crossref","is-referenced-by-count":85,"title":["Autonomous navigation of UAV in large-scale unknown complex environment with deep reinforcement learning"],"prefix":"10.1109","author":[{"given":"Chao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xudong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref11","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume":"2014","author":"silver","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref12","author":"heess","year":"2015","journal-title":"Memory-based control with recurrent neural networks"},{"key":"ref13","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref14","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20400"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-015-0292-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907839"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/70.938381"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364908098412"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS.2014.6842265"},{"key":"ref1","year":"0","journal-title":"Amazon Prime Air"},{"key":"ref9","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"}],"event":{"name":"2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","location":"Montreal, QC","start":{"date-parts":[[2017,11,14]]},"end":{"date-parts":[[2017,11,16]]}},"container-title":["2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8303183\/8308583\/08309082.pdf?arnumber=8309082","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,4,9]],"date-time":"2018-04-09T21:08:33Z","timestamp":1523308113000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8309082\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/globalsip.2017.8309082","relation":{},"subject":[],"published":{"date-parts":[[2017,11]]}}}