{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T20:19:05Z","timestamp":1777407545865,"version":"3.51.4"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"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":[[2019,4]]},"DOI":"10.1109\/codit.2019.8820575","type":"proceedings-article","created":{"date-parts":[[2019,9,3]],"date-time":"2019-09-03T01:09:32Z","timestamp":1567472972000},"page":"91-96","source":"Crossref","is-referenced-by-count":11,"title":["Large space dimension Reinforcement Learning for Robot Position\/Force Discrete Control"],"prefix":"10.1109","author":[{"given":"Adolfo","family":"Perrusquia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alberto","family":"Soria","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/3516.789685"},{"key":"ref11","first-page":"1","article-title":"Impedance control: an approach to manipulation, journal of dynamic systems","author":"hogan","year":"1985","journal-title":"Measurement and Control"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2378812"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TOH.2016.2518670"},{"key":"ref14","first-page":"1124","article-title":"Pid admittance control for an upper limb exoskeleton","author":"yu","year":"0","journal-title":"American Control Conference"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1994.351417"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/0278364905056347"},{"key":"ref17","article-title":"Techniques for environment parameter estimation during telemanipulation","author":"yakamoto","year":"0","journal-title":"Proc of the 2nd Biennial IEEE\/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139801"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2009.09.011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2170565"},{"key":"ref6","first-page":"1473","author":"guo","year":"0","journal-title":"K-means clustering based reinforcement learning algorithm for automatic control in robots"},{"key":"ref5","article-title":"Clustering with reinforcement learning","volume":"4881","author":"barbakh","year":"2007","journal-title":"Intelligent Data Engineering and Automated Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2012.101"},{"key":"ref7","article-title":"Semi-unsupervised clustering using reinforcement learning","author":"bose","year":"0","journal-title":"Proceedings of the Twenty-Ninth International Florida Artificial Intelligence Research Society Conference"},{"key":"ref2","author":"busoniu","year":"2010","journal-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.363573"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/089976699300016025"},{"key":"ref20","article-title":"Reinforcement learning and feedback control using natural decision methods to desgin optimal adaptive controllers","author":"lewis","year":"2012","journal-title":"IEEE Control Systems Magazine"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2017.08.2320"},{"key":"ref21","author":"kelly","year":"2003","journal-title":"Control de Movimiento de Robots Manipuladores"},{"key":"ref24","author":"astrom","year":"1989","journal-title":"Adaptive Control"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114724"}],"event":{"name":"2019 6th International Conference on Control, Decision and Information Technologies (CoDIT)","location":"Paris, France","start":{"date-parts":[[2019,4,23]]},"end":{"date-parts":[[2019,4,26]]}},"container-title":["2019 6th International Conference on Control, Decision and Information Technologies (CoDIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8806019\/8820291\/08820575.pdf?arnumber=8820575","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T20:17:50Z","timestamp":1658261870000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8820575\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/codit.2019.8820575","relation":{},"subject":[],"published":{"date-parts":[[2019,4]]}}}