{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:36:35Z","timestamp":1740101795102,"version":"3.37.3"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,3,24]],"date-time":"2023-03-24T00:00:00Z","timestamp":1679616000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,24]],"date-time":"2023-03-24T00:00:00Z","timestamp":1679616000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,3,24]]},"DOI":"10.1109\/cbs55922.2023.10115383","type":"proceedings-article","created":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T18:35:36Z","timestamp":1683570936000},"page":"326-331","source":"Crossref","is-referenced-by-count":0,"title":["An active pursuit strategy for autonomous mobile robots based on deep reinforcement learning"],"prefix":"10.1109","author":[{"given":"Yingnan","family":"Gao","sequence":"first","affiliation":[{"name":"Wuhan University of Science and Technology,Control Science and Engineering,Wuhan,China,430081"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Cheng","sequence":"additional","affiliation":[{"name":"Institute of Robotics and Intelligent Systems, Wuhan University of Science and Technology,Wuhan,China,430081"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"He","sequence":"additional","affiliation":[{"name":"Wuhan University of Science and Technology,School of Information Science and Engineering\/School of Artificial Intelligence,Wuhan,China,430081"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Duanchu","family":"Wang","sequence":"additional","affiliation":[{"name":"Wuhan University of Science and Technology,School of Information Science and Engineering\/School of Artificial Intelligence,Wuhan,China,430081"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref12","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/CCC52363.2021.9550047"},{"key":"ref14","article-title":"Soft actor-critic for discrete action settings","author":"christodoulou","year":"2019","journal-title":"arXiv preprint arXiv 1910 07470"},{"key":"ref11","first-page":"1861","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref10","first-page":"22905","article-title":"Causal influence detection for improving efficiency in reinforcement learning","volume":"34","author":"seitzer","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CBS46900.2019.9114417"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abj2908"},{"key":"ref8","first-page":"1","article-title":"Reinforcement learning in robotic applications: a comprehensive survey","author":"singh","year":"2021","journal-title":"Artificial Intelligence Review"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812046"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3145059"},{"key":"ref4","article-title":"Bayesian reinforcement learning: Real-world learning faster than simulations","author":"huang","year":"2020","journal-title":"arXiv preprint arXiv 2007 10035"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2018.2877499"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SEFM.2003.1236202"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/app12094769"}],"event":{"name":"2022 IEEE International Conference on Cyborg and Bionic Systems (CBS)","start":{"date-parts":[[2023,3,24]]},"location":"Wuhan, China","end":{"date-parts":[[2023,3,26]]}},"container-title":["2022 IEEE International Conference on Cyborg and Bionic Systems (CBS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10115317\/10115301\/10115383.pdf?arnumber=10115383","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T17:30:16Z","timestamp":1685381416000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10115383\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,24]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/cbs55922.2023.10115383","relation":{},"subject":[],"published":{"date-parts":[[2023,3,24]]}}}