{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T17:27:33Z","timestamp":1782494853809,"version":"3.54.5"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61701134"],"award-info":[{"award-number":["61701134"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Equipment Pre-Research Fund of China","award":["61404150101"],"award-info":[{"award-number":["61404150101"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2905649","type":"journal-article","created":{"date-parts":[[2019,3,18]],"date-time":"2019-03-18T23:42:11Z","timestamp":1552952531000},"page":"37432-37447","source":"Crossref","is-referenced-by-count":34,"title":["Deep Reinforcement Learning for Target Searching in Cognitive Electronic Warfare"],"prefix":"10.1109","volume":"7","author":[{"given":"Shixun","family":"You","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Diao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2287-6279","authenticated-orcid":false,"given":"Lipeng","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","author":"espeholt","year":"2018","journal-title":"IM-PALA Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures"},{"key":"ref38","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf Int Conf Mach Learn"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2015.09.006"},{"key":"ref32","author":"santoro","year":"2016","journal-title":"One-shot learning with memory-augmented neural networks"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073602"},{"key":"ref30","first-page":"2790","article-title":"Control of memory, active perception, and action in minecraft","author":"oh","year":"2016","journal-title":"Proc Int Conf Int Conf Mach Learn"},{"key":"ref37","first-page":"1889","article-title":"Trust region policy optimization","volume":"37","author":"schulman","year":"2015","journal-title":"Comput Sci"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2008.11.008"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"volodymyr","year":"2015","journal-title":"Nature"},{"key":"ref34","first-page":"2829","article-title":"Continuous deep q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"Proc Int Conf Int Conf Mach Learn"},{"key":"ref10","first-page":"1215","article-title":"Research on force assignment for ground-to-air radar jamming system based on chaos genetic algorithms","author":"wei","year":"2016","journal-title":"Proc Chin Control Decision Conf"},{"key":"ref40","author":"mnih","year":"2016","journal-title":"Asynchronous methods for deep reinforcement learning"},{"key":"ref11","first-page":"368","article-title":"IIGA based algorithm for cooperative jamming resource allocation","author":"zhai","year":"2010","journal-title":"Proc Asia Pacific Conf Postgraduate Res Microelectron Electron (PrimeAsia)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1049\/iet-rsn.2016.0277"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA.2016.7505284"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS.2013.6564676"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"666","DOI":"10.3390\/s16050666","article-title":"Enabling UAV navigation with sensor and environmental uncertainty in cluttered and GPS-denied environments","volume":"16","author":"vanegas","year":"2016","journal-title":"SENSORS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s12217-018-9650-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-007-9081-4"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2170333"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.11.007"},{"key":"ref28","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1121\/1.5035588"},{"key":"ref27","first-page":"1","article-title":"Reinforcement learning through asynchronous advantage actor-critic on a gpu","author":"babaeizadeh","year":"2017","journal-title":"Proc ICLR"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1518\/155534310X522851","article-title":"Adaptive automation based on an object-oriented task model: Implementation and evaluation in a realistic c2 environment","volume":"4","author":"greef","year":"2010","journal-title":"J Cognit Eng Decis Making"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/int.20413"},{"key":"ref29","author":"weber","year":"2017","journal-title":"Imagination-Augmented Agents for Deep Reinforcement Learning"},{"key":"ref5","first-page":"1","article-title":"Cognitive multistatic auv networks","author":"braca","year":"2014","journal-title":"Proc Int Conf Inf Fusion"},{"key":"ref8","first-page":"1002","article-title":"Bayesian terrain-based underwater navigation using an improved state-space model","author":"chen","year":"2012","journal-title":"Proc 3rd Int Conf Digit Manuf Autom"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICNIDC.2009.5360942"},{"key":"ref2","first-page":"245","article-title":"Using fuzzy cognitive maps to analyze the information processing model of situation awareness","author":"xue","year":"2014","journal-title":"Proc Int Conf Intell Hum -Mach Syst Cybern"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.2514\/6.2006-6197"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/02564602.2003.11417078"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1109\/MSP.2017.2743240","article-title":"Deep reinforcement learning: A brief survey","volume":"34","author":"kai","year":"2017","journal-title":"IEEE Signal Process Mag"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020564024509"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0102-6"},{"key":"ref42","author":"kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref24","article-title":"Deep reinforcement learning with double q-learning","author":"hasselt","year":"0","journal-title":"Comput Sci"},{"key":"ref41","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"Proc Int Conf Int Conf Mach Learn"},{"key":"ref23","author":"bhatti","year":"2016","journal-title":"Torr Playing doom with slam-augmented deep reinforcement learning"},{"key":"ref44","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Int Conf Mach Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989326"},{"key":"ref43","article-title":"Deep kalman filters","author":"krishnan","year":"0","journal-title":"Comput Sci"},{"key":"ref25","first-page":"187a","article-title":"Continuous control with deep reinforcement learning","volume":"8","author":"lillicrap","year":"2015","journal-title":"Comput Sci"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08668391.pdf?arnumber=8668391","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,10]],"date-time":"2021-08-10T19:40:46Z","timestamp":1628624446000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8668391\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2905649","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}