{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T15:55:29Z","timestamp":1782402929387,"version":"3.54.5"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T00:00:00Z","timestamp":1670198400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T00:00:00Z","timestamp":1670198400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001807","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073183"],"award-info":[{"award-number":["62073183"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,5]]},"DOI":"10.1109\/robio55434.2022.10011769","type":"proceedings-article","created":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T18:51:38Z","timestamp":1674067898000},"page":"1775-1780","source":"Crossref","is-referenced-by-count":3,"title":["High maneuverability control of Single-track Two-wheeled Robot in Narrow Terrain based on Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Qingyuan","family":"Zheng","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China,100084"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianjin","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Mechatronics Engineering, Harbin Institute of Technology,Harbin,China,150006"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Deng","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China,100084"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Tian","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China,100084"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhang","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China,100084"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Liang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China,100084"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2008.927406"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2005.1499389"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IECON43393.2020.9254572"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2002.1023121"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2018.8665347"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5979841"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1163\/016918610X538462"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2014.6859392"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2015.7419087"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1998.680749"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2019.2922068"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechatronics.2020.102386"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2008.2004349"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s12206-015-0442-1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-021-06380-9"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"issue":"3","key":"ref17","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Machine learning"},{"key":"ref18","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint"},{"key":"ref19","volume-title":"Deep learning","author":"Goodfellow","year":"2016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016191"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref23","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"International conference on machine learning, 2014: PMLR","author":"Silver"},{"key":"ref24","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2017","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Deep reinforcement learning in param-eterized action space","author":"Hausknecht","year":"2015","journal-title":"arXiv preprint"},{"key":"ref27","first-page":"1587","article-title":"Addressing function approx-imation error in actor-critic methods","volume-title":"International conference on machine learning, 2018: PMLR","author":"Fujimoto"},{"key":"ref28","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International conference on machine learning, 2015: PMLR","author":"Schulman"},{"key":"ref29","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/sym11020290"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA52036.2021.9512587"}],"event":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","location":"Jinghong, China","start":{"date-parts":[[2022,12,5]]},"end":{"date-parts":[[2022,12,9]]}},"container-title":["2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10011626\/10011636\/10011769.pdf?arnumber=10011769","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T09:53:09Z","timestamp":1707472389000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10011769\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,5]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/robio55434.2022.10011769","relation":{},"subject":[],"published":{"date-parts":[[2022,12,5]]}}}