{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:17:35Z","timestamp":1759331855835,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T00:00:00Z","timestamp":1697414400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T00:00:00Z","timestamp":1697414400000},"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":[[2023,10,16]]},"DOI":"10.1109\/iecon51785.2023.10312041","type":"proceedings-article","created":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T13:52:10Z","timestamp":1700142730000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Reinforcement Learning Based Path Tracking Control Method for Unmanned Bicycle on Complex Terrain"],"prefix":"10.1109","author":[{"given":"Benyan","family":"Huo","sequence":"first","affiliation":[{"name":"School of Electrical and Information Engineering, Zhengzhou University,Zhengzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Long","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Zhengzhou University,Zhengzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanhong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Zhengzhou University,Zhengzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyu","family":"Sha","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Zhengzhou University,Zhengzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA52036.2021.9512587"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2008.2011621"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3268524"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"journal-title":"Pybullet a python module for physics simulation for games robotics and machine learning","year":"2016","author":"coumans","key":"ref20"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IECON43393.2020.9254787"},{"key":"ref10","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/00423114.2010.503810"},{"key":"ref1","first-page":"266","article-title":"Bicycle: The history","volume":"93","author":"schoonmaker","year":"2005","journal-title":"American Scientist"},{"key":"ref17","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"ArXiv Preprint"},{"journal-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"ref16"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref18","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref8","volume":"37","author":"rummery","year":"1994","journal-title":"On-line Q-learning using connectionist systems"},{"key":"ref7","first-page":"463","article-title":"Learning to drive a bicycle using reinforcement learning and shaping","volume":"98","author":"randl\u00f8v","year":"0","journal-title":"ICML"},{"key":"ref9","first-page":"413","article-title":"Controlling bicycle using deep deterministic policy gradient algorithm","author":"chung","year":"0","journal-title":"2017 14th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/asjc.303"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICINFA.2010.5512251"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1541\/ieejias.132.651"}],"event":{"name":"IECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society","start":{"date-parts":[[2023,10,16]]},"location":"Singapore, Singapore","end":{"date-parts":[[2023,10,19]]}},"container-title":["IECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10311571\/10311610\/10312041.pdf?arnumber=10312041","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T13:11:17Z","timestamp":1701263477000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10312041\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,16]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/iecon51785.2023.10312041","relation":{},"subject":[],"published":{"date-parts":[[2023,10,16]]}}}