{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T13:26:34Z","timestamp":1762953994000,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T00:00:00Z","timestamp":1718668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T00:00:00Z","timestamp":1718668800000},"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":["52202502"],"award-info":[{"award-number":["52202502"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,18]]},"DOI":"10.1109\/icca62789.2024.10591821","type":"proceedings-article","created":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T17:19:13Z","timestamp":1721927953000},"page":"665-672","source":"Crossref","is-referenced-by-count":1,"title":["A Guided-to-Autonomous Policy Learning Method of Deep Reinforcement Learning in Path Planning"],"prefix":"10.1109","author":[{"given":"Wang","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Astronautics, Northwestern Polytechnical University,Xi'an,China"}]},{"given":"Ye","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Astronautics, Northwestern Polytechnical University,Xi'an,China"}]},{"given":"Haoyu","family":"Li","sequence":"additional","affiliation":[{"name":"School of Astronautics, Northwestern Polytechnical University,Xi'an,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2021.3071723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1201\/9781439864135-43"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3067310"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3300576"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2023.115208"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3222989"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3240758"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3153352"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2869644"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3290511"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3064461"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3292004"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.01.087"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110660"},{"issue":"5","key":"ref15","first-page":"847","article-title":"Trajectory planning for hypersonic vehicle combined with reinforcement learning and evolutionary algorithms","volume":"39","author":"Chi","year":"2022","journal-title":"Control Theory Technol."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110601"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3061372"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110761"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref20","first-page":"289","article-title":"Part IV: Environment Design","author":"Graesser","year":"2019","journal-title":"Foundations of Deep Reinforcement Learning: Theory and Practice in Python, 1st, Addison-Wesley Professional"},{"issue":"2","key":"ref21","first-page":"327083","article-title":"Research on maneuvering decision-making of multi-UAV attack-defence confrontation based on PER-MATD3","volume":"43","author":"Wu","year":"2023","journal-title":"Acta Aeronautica et Astronautica Sinica"},{"key":"ref22","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint"},{"key":"ref23","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3101544"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3192480"}],"event":{"name":"2024 IEEE 18th International Conference on Control & Automation (ICCA)","start":{"date-parts":[[2024,6,18]]},"location":"Reykjav\u00edk, Iceland","end":{"date-parts":[[2024,6,21]]}},"container-title":["2024 IEEE 18th International Conference on Control & Automation (ICCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10591777\/10591797\/10591821.pdf?arnumber=10591821","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,26]],"date-time":"2024-07-26T04:52:32Z","timestamp":1721969552000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10591821\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,18]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icca62789.2024.10591821","relation":{},"subject":[],"published":{"date-parts":[[2024,6,18]]}}}