{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T19:04:07Z","timestamp":1773774247365,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096457","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["UAV Local Path Planning Based on Improved Proximal Policy Optimization Algorithm"],"prefix":"10.1109","author":[{"given":"Jiahao","family":"Xu","sequence":"first","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics,Collaborative Innovation Center of Novel Software Technology and Industrialization"}]},{"given":"Xufeng","family":"Yan","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics,Collaborative Innovation Center of Novel Software Technology and Industrialization"}]},{"given":"Cui","family":"Peng","sequence":"additional","affiliation":[{"name":"Dalian Naval Academy"}]},{"given":"Xinquan","family":"Wu","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics,Collaborative Innovation Center of Novel Software Technology and Industrialization"}]},{"given":"Lipeng","family":"Gu","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics,Collaborative Innovation Center of Novel Software Technology and Industrialization"}]},{"given":"Yanbiao","family":"Niu","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics,Collaborative Innovation Center of Novel Software Technology and Industrialization"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref12","article-title":"Ptr-ppo: Proximal policy optimization with prioritized trajectory replay","author":"liang","year":"2021"},{"key":"ref15","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref14","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015"},{"key":"ref20","first-page":"1388","article-title":"Adaptive interfered fluid dynamic system algorithm based on deep reinforcement learning framework","author":"zhang","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.108194"},{"key":"ref22","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2017.8122622"},{"key":"ref21","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-019-01112-z"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2020.3017677"},{"key":"ref17","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015"},{"key":"ref16","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/j.cja.2020.12.027","article-title":"Relevant experience learning: A deep reinforcement learning method for uav autonomous motion planning in complex unknown environments","volume":"34","author":"zijian","year":"2021","journal-title":"Chinese Journal of Aeronautics"},{"key":"ref18","article-title":"Reinforcement learning: An introduction","author":"sutton","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890773"},{"key":"ref7","article-title":"An improved dyna-q algorithm for mobile robot path planning in unknown dynamic environment","author":"pei","year":"2021","journal-title":"IEEE Transactions on Systems Man and Cybernetics Systems"},{"key":"ref9","article-title":"Prioritized experience replay","author":"schaul","year":"2015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746264"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2020.11.012"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054054"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8430925"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096457.pdf?arnumber=10096457","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T17:47:30Z","timestamp":1749577650000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096457\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096457","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}