{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:51:03Z","timestamp":1776880263924,"version":"3.51.2"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276202"],"award-info":[{"award-number":["62276202"]}],"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":["62106186"],"award-info":[{"award-number":["62106186"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Basic Research Plan in Shaanxi Province of China","award":["2022JQ-670"],"award-info":[{"award-number":["2022JQ-670"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["QTZX22047"],"award-info":[{"award-number":["QTZX22047"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tetci.2024.3369485","type":"journal-article","created":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T18:12:08Z","timestamp":1711131128000},"page":"2625-2639","source":"Crossref","is-referenced-by-count":31,"title":["Path Planning for Unmanned Aerial Vehicle via Off-Policy Reinforcement Learning With Enhanced Exploration"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8238-0154","authenticated-orcid":false,"given":"Zhengjun","family":"Wang","sequence":"first","affiliation":[{"name":"School of Mathematics and Statistics, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi&#x0027;an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3853-0771","authenticated-orcid":false,"given":"Weifeng","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi&#x0027;an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9950-9848","authenticated-orcid":false,"given":"Genghui","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1152-6780","authenticated-orcid":false,"given":"Zhenkun","family":"Wang","sequence":"additional","affiliation":[{"name":"School of System Design and Intelligent Manufacturing, Southern University of Science and Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0415-8556","authenticated-orcid":false,"given":"Maoguo","family":"Gong","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding, International Research Center for Intelligent Perception and Computation, Ministry of Education, Xidian University, Xi&#x0027;an, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2022.3140796"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2021.100956"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3050960"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2014.2381359"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/359156.359164"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/BF01386390"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1994.351061"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ChiCC.2014.6896718"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1142\/S2301385014500058"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2016.03.049"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/70.508439"},{"key":"ref13","first-page":"98","article-title":"Rapidly-exploring random trees: A new tool for path planning","author":"LaValle","year":"1998"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844730"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2015.7081657"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/AIM.2017.8014251"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1177\/027836498600500106"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/ChiCC.2018.8483405"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CCDC49329.2020.9163979"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2021.3066606"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2022.3141819"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2022.3168836"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.08.008"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-020-05483-6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.12.016"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2021.101005"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/0020294020915727"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2019.08.018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107796"},{"key":"ref30","volume-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2019.02.006"},{"key":"ref32","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.06.066"},{"key":"ref34","article-title":"Prioritized experience replay","author":"Schaul","year":"2015"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref36","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2016"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-019-01073-3"},{"key":"ref38","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref39","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2884797"},{"key":"ref42","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.05.097"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3026638"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3060403"},{"key":"ref46","first-page":"13859","article-title":"Safe reinforcement learning by imagining the near future","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Thomas","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3089120"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3121747"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/APCCAS55924.2022.10090255"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCR55715.2022.10053884"},{"key":"ref51","first-page":"1068","article-title":"On-line policy improvement using Monte-Carlo search","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tesauro","year":"1996"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2011.03.007"},{"key":"ref53","first-page":"10376","article-title":"Keeping your distance: Solving sparse reward tasks using self-balancing shaped rewards","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Trott","year":"2019"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref55","article-title":"Meta-learning curiosity algorithms","author":"Alet","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20743"},{"key":"ref57","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bellemare","year":"2016"},{"key":"ref58","first-page":"4","article-title":"A study of count-based exploration for deep reinforcement learning","volume-title":"Proc. 31st Conf. Neural Inf. Process. Syst.","author":"Tang","year":"2017"},{"key":"ref59","first-page":"2721","article-title":"Count-based exploration with neural density models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ostrovski","year":"2017"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7433297\/10538459\/10478216.pdf?arnumber=10478216","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T04:53:00Z","timestamp":1725684780000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10478216\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":59,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2024.3369485","relation":{},"ISSN":["2471-285X"],"issn-type":[{"value":"2471-285X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}