{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T09:48:48Z","timestamp":1762508928706,"version":"build-2065373602"},"reference-count":24,"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\/robio55434.2022.10011757","type":"proceedings-article","created":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T18:51:38Z","timestamp":1674067898000},"page":"1769-1774","source":"Crossref","is-referenced-by-count":5,"title":["Ramp Jump Control of Single-track Two-wheeled Robot using Reinforcement Learning with Demonstration Data"],"prefix":"10.1109","author":[{"given":"Qingyuan","family":"Zheng","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianjin","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Mechatronics Engineering, Harbin Institute of Technology,Harbin,China,150006"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Deng","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhang","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Liang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"120","key":"ref1","first-page":"312","article-title":"The stability of the motion of a bicycle","volume":"30","author":"Whipple","year":"1899","journal-title":"Quarterly Journal of Pure and Applied Mathematics"},{"key":"ref2","article-title":"Dynamic inversion of nonlinear maps with applications to nonlinear control and robotics","author":"Getz","year":"1995","journal-title":"University of California, Berkeley"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2005.1499389"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2018.8665347"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814916"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2008.927406"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2002.1023121"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2014.6859392"},{"key":"ref9","first-page":"1057","article-title":"Stabilizing of bike robot with variable configured balancer","volume-title":"SICE Annual Conference 2011","author":"Kawaguchi"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s12206-015-0442-1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/sym11020290"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA52036.2021.9512587"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/01423312211037847"},{"key":"ref14","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"International conference on machine learning","author":"Silver"},{"key":"ref15","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"Sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International conference on machine learning","author":"Fujimoto"},{"key":"ref18","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"International conference on machine learning","author":"Mnih"},{"key":"ref19","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International conference on machine learning","author":"Schulman"},{"key":"ref20","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref22","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2017","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref24","article-title":"Double Q-learning","volume":"23","author":"Hasselt","year":"2010","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","start":{"date-parts":[[2022,12,5]]},"location":"Jinghong, China","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\/10011757.pdf?arnumber=10011757","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T08:19:29Z","timestamp":1707466769000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10011757\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,5]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/robio55434.2022.10011757","relation":{},"subject":[],"published":{"date-parts":[[2022,12,5]]}}}