{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T15:24:15Z","timestamp":1777735455297,"version":"3.51.4"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017607","name":"Shenzhen Fundamental Research Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100017607","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610970","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"5119-5125","source":"Crossref","is-referenced-by-count":5,"title":["An Environmental-Complexity-Based Navigation Method Based on Hierarchical Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Pengbin","family":"Chen","sequence":"first","affiliation":[{"name":"The Harbin Institute of Technology,Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and School of Mechanical Engineering and Automation,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"The Harbin Institute of Technology,Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and School of Mechanical Engineering and Automation,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanjie","family":"Li","sequence":"additional","affiliation":[{"name":"The Harbin Institute of Technology,Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and School of Mechanical Engineering and Automation,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuaikang","family":"Ma","sequence":"additional","affiliation":[{"name":"The Harbin Institute of Technology,Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and School of Mechanical Engineering and Automation,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-020-03526-7"},{"key":"ref2","volume-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref3","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref4","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International Conference on Machine Learning","author":"Fujimoto"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197148"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560951"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811797"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CASE48305.2020.9217023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/RCAR.2016.7784001"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794134"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341540"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0467-z"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2007.4282736"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA.2019.8899904"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160371"},{"key":"ref20","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International Conference on Machine Learning","author":"Haarnoja"},{"key":"ref21","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/100.580977"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341783"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610970.pdf?arnumber=10610970","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:59:48Z","timestamp":1723269588000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610970\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610970","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}