{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:16:30Z","timestamp":1759331790366,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,6]]},"DOI":"10.1109\/urai.2017.7992765","type":"proceedings-article","created":{"date-parts":[[2017,8,9]],"date-time":"2017-08-09T16:04:15Z","timestamp":1502294655000},"page":"413-417","source":"Crossref","is-referenced-by-count":12,"title":["Controlling bicycle using deep deterministic policy gradient algorithm"],"prefix":"10.1109","author":[{"given":"Le Pham","family":"Tuyen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"TaeChoong","family":"Chung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Model-free least-squares policy iteration","volume":"14","author":"lagoudakis","year":"2001","journal-title":"NIPS"},{"journal-title":"Deterministic policy gradient algorithms","year":"2014","author":"lever","key":"ref11"},{"journal-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"year":"0","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"journal-title":"Adam A method for stochastic optimization","year":"2014","author":"kingma","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2004.180"},{"journal-title":"Murata Boy","year":"0","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2007.1857"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/cae.21666"},{"journal-title":"Bicycle Robot","year":"0","key":"ref5"},{"key":"ref8","article-title":"Learning to Drive a Bicycle Using Reinforcement Learning and Shaping","volume":"98","author":"randlv","year":"1998","journal-title":"ICML"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2013.6759903"},{"key":"ref2","article-title":"Some recent developments in bicycle dynamics","author":"schwab","year":"2007","journal-title":"Proc 11th World Congress in Mechanism and Machine Science"},{"journal-title":"Bicycle&#821The History","year":"2004","author":"herlihy","key":"ref1"},{"key":"ref9","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"}],"event":{"name":"2017 14th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","start":{"date-parts":[[2017,6,28]]},"location":"Jeju","end":{"date-parts":[[2017,7,1]]}},"container-title":["2017 14th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7983000\/7992653\/07992765.pdf?arnumber=7992765","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,8,29]],"date-time":"2017-08-29T15:26:45Z","timestamp":1504020405000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7992765\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/urai.2017.7992765","relation":{},"subject":[],"published":{"date-parts":[[2017,6]]}}}