{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T19:55:45Z","timestamp":1775678145293,"version":"3.50.1"},"reference-count":34,"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":["61573246"],"award-info":[{"award-number":["61573246"]}],"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":["61603255"],"award-info":[{"award-number":["61603255"]}],"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":["61873169"],"award-info":[{"award-number":["61873169"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP160103567"],"award-info":[{"award-number":["DP160103567"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Twilight Program of China","award":["18CG52"],"award-info":[{"award-number":["18CG52"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2918703","type":"journal-article","created":{"date-parts":[[2019,5,24]],"date-time":"2019-05-24T19:58:51Z","timestamp":1558727931000},"page":"67319-67330","source":"Crossref","is-referenced-by-count":136,"title":["Path Planning via an Improved DQN-Based Learning Policy"],"prefix":"10.1109","volume":"7","author":[{"given":"Liangheng","family":"Lv","sequence":"first","affiliation":[{"name":"Department of Control Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7648-2358","authenticated-orcid":false,"given":"Sunjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China"}]},{"given":"Derui","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China"}]},{"given":"Yongxiong","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2018.8647614"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-017-3241-z"},{"key":"ref31","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 Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2869644"},{"key":"ref10","author":"szepesvri","year":"2011","journal-title":"Wiley Encyclopedia of Operations Research and Management Science"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1109\/TNN.2004.842673","article-title":"Reinforcement learning: An introduction","volume":"16","author":"kaelbling","year":"2005","journal-title":"IEEE Trans Neural Netw"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.06.066"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref14","author":"busoniu","year":"2010","journal-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SAINT-W.2006.20"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICNC.2008.694"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"581","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref18","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc 33nd Int Conf Mach Learn"},{"key":"ref19","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref28","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/128762.128764"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s007780050040"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1985.1087247"},{"key":"ref29","article-title":"FractalNet: Ultra-deep neural networks without residuals","author":"larsson","year":"2016","journal-title":"arXiv 1605 07648"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1990.126042"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/3477.484436"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICEC.1997.592326"},{"key":"ref2","first-page":"1","article-title":"Hierarchical A*: Searching abstraction hierarchies efficiently","author":"holte","year":"1996","journal-title":"Proc 13th Nat Conf Artif Intell"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1080\/21642583.2018.1471426"},{"key":"ref1","first-page":"28","article-title":"A formal basis for the heuristic determination of minimum cost paths","volume":"4","author":"hart","year":"1972","journal-title":"IEEE Trans Syst Sci Cybern"},{"key":"ref20","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref22","article-title":"Incentivizing exploration in reinforcement learning with deep predictive models","author":"stadie","year":"2015","journal-title":"arXiv 1507 00814"},{"key":"ref21","first-page":"4026","article-title":"Deep exploration via bootstrapped DQN","author":"osband","year":"2016","journal-title":"Proc Neural Inf Process Syst Conf"},{"key":"ref24","first-page":"176","article-title":"Averaged-DQN: Variance reduction and stabilization for deep reinforcement learning","author":"anschel","year":"2016","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref23","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","article-title":"Maximum entropy deep inverse reinforcement learning","author":"wulfmeier","year":"2015","journal-title":"arXiv 1507 04888"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08721655.pdf?arnumber=8721655","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T17:35:37Z","timestamp":1715708137000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8721655\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2918703","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}