{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T17:50:38Z","timestamp":1783705838121,"version":"3.55.0"},"reference-count":39,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2018YFC0810204"],"award-info":[{"award-number":["2018YFC0810204"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2933002","type":"journal-article","created":{"date-parts":[[2019,8,6]],"date-time":"2019-08-06T00:07:36Z","timestamp":1565050056000},"page":"117227-117245","source":"Crossref","is-referenced-by-count":137,"title":["UAV Autonomous Target Search Based on Deep Reinforcement Learning in Complex Disaster Scene"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8498-3881","authenticated-orcid":false,"given":"Chunxue","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7769-5646","authenticated-orcid":false,"given":"Bobo","family":"Ju","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0394-4635","authenticated-orcid":false,"given":"Naixue","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2079-0989","authenticated-orcid":false,"given":"Guangquan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5909-1347","authenticated-orcid":false,"given":"Hongyan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuefeng","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2899972"},{"key":"ref38","article-title":"Fine-grained age estimation in the wild with attention LSTM networks","author":"zhang","year":"2018","journal-title":"arXiv 1805 10445"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206161"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460655"},{"key":"ref31","first-page":"1","article-title":"Enhancements for real-time Monte-Carlo tree search in general video game playing","author":"soemers","year":"2017","journal-title":"Proc IEEE Conf Comput Intell Games (CIG)"},{"key":"ref30","first-page":"2829","article-title":"Continuous deep q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref36","article-title":"Beyond Monte Carlo tree search: Playing go with deep alternative neural network and long-term evaluation","author":"wang","year":"2017","journal-title":"arXiv 1706 04052"},{"key":"ref35","article-title":"Deep learning for reward design to improve Monte Carlo tree search in ATARI games","author":"guo","year":"2016","journal-title":"arXiv 1604 07095"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1051\/cocv\/2017019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2812794"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2817486"},{"key":"ref12","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref13","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv 1511 05952"},{"key":"ref14","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2015","journal-title":"arXiv 1511 06581"},{"key":"ref15","article-title":"A distributional perspective on reinforcement learning","author":"bellemare","year":"2017","journal-title":"arXiv 1707 06887"},{"key":"ref16","article-title":"Noisy networks for exploration","author":"fortunato","year":"2017","journal-title":"arXiv 1706 10295"},{"key":"ref17","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2017","journal-title":"arXiv 1710 02298"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080775"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5849\/FS-2016-078R2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3001773.3001797"},{"key":"ref4","article-title":"Collaborative tasks planning research for multi-UAV based on ant colony algorithm","author":"zhang","year":"2017","journal-title":"J Beijing Univ Civil Eng Archit"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.321"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989656"},{"key":"ref6","article-title":"Towards vision-based deep reinforcement learning for robotic motion control","author":"zhang","year":"2015","journal-title":"arXiv 1511 03791"},{"key":"ref29","article-title":"Combining policy gradient and Q-learning","author":"o\u2019donoghue","year":"2017","journal-title":"arXiv 1611 01626"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/sym10070294"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2015.09.039"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2824849"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-6062-x"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s12046-014-0275-0"},{"key":"ref20","article-title":"A unified view of entropy-regularized Markov decision processes","author":"neu","year":"2017","journal-title":"arXiv 1705 07798"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66335-7_13"},{"key":"ref21","article-title":"Threshold constraints with guarantees for parity objectives in Markov decision processes","author":"berthon","year":"2017","journal-title":"arXiv 1702 05472"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800085"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-018-0802-z"},{"key":"ref26","author":"lample","year":"2016","journal-title":"Playing fps games with deep reinforcement learning"},{"key":"ref25","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08787847.pdf?arnumber=8787847","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,10]],"date-time":"2021-08-10T19:40:29Z","timestamp":1628624429000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8787847\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2933002","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}