{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T20:54:48Z","timestamp":1765486488409,"version":"3.37.3"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100010751","name":"Chilean National Research and Development Agency (ANID) through the Project Fondo Nacional de Desarrollo Cient\u00edfico y Tecnol\u00f3gico","doi-asserted-by":"publisher","award":["1191188"],"award-info":[{"award-number":["1191188"]}],"id":[{"id":"10.13039\/501100010751","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007776","name":"Direcci\u00f3n de Investigaci\u00f3n (DI)-Pontificia Universidad Cat\u00f3lica de Valpara\u00edso","doi-asserted-by":"publisher","award":["039.437"],"award-info":[{"award-number":["039.437"]}],"id":[{"id":"10.13039\/501100007776","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Spanish Ministry of Economy and Competitiveness through the Projects","award":["RTI2018-094665-B-I00","ENE2015-64914-C3-3-R"],"award-info":[{"award-number":["RTI2018-094665-B-I00","ENE2015-64914-C3-3-R"]}]},{"name":"Spanish Ministry of Science and Innovation through the Project","award":["PID2019-108377RB-C32"],"award-info":[{"award-number":["PID2019-108377RB-C32"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3018026","type":"journal-article","created":{"date-parts":[[2020,8,19]],"date-time":"2020-08-19T20:10:30Z","timestamp":1597867830000},"page":"152941-152951","source":"Crossref","is-referenced-by-count":28,"title":["Reinforcement Learning for Position Control Problem of a Mobile Robot"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2186-4126","authenticated-orcid":false,"given":"Gonzalo","family":"Farias","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9968-960X","authenticated-orcid":false,"given":"Gonzalo","family":"Garcia","sequence":"additional","affiliation":[]},{"given":"Guelis","family":"Montenegro","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4478-6626","authenticated-orcid":false,"given":"Ernesto","family":"Fabregas","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7652-5338","authenticated-orcid":false,"given":"Sebastian","family":"Dormido-Canto","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2405-8771","authenticated-orcid":false,"given":"Sebastian","family":"Dormido","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1007\/978-3-642-35197-6_9"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1016\/S0010-4655(03)00440-5"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/CCA.2016.7587920"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1016\/j.ifacol.2018.06.084"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1007\/s10846-015-0229-8"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/CERMA.2012.42"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1109\/IROS.2008.4650937"},{"key":"ref36","first-page":"2333","article-title":"BF-PSO optimized PID controller design using ISE, IAE, IATE and MSE error criteria","volume":"2","author":"soni","year":"2013","journal-title":"Int J Adv Res Comput Eng Technol"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1016\/j.ifacol.2017.08.1721"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1016\/j.ifacol.2016.07.157"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.3166\/ejc.16.144-155"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/CCDC.2019.8833053"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/IWOBI.2017.7985533"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1016\/j.neucom.2011.06.035"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1155\/2016\/9548482"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/TIE.2019.2935976"},{"key":"ref16","first-page":"150","article-title":"A wheeled mobile robot with obstacle avoidance capability","author":"gonzalez","year":"2004","journal-title":"Mechanica Technologia"},{"year":"2018","author":"sutton","journal-title":"Reinforcement Learning An Introduction","key":"ref17"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1201\/9781439821091"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/EMEIT.2011.6023706"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1007\/BF00992698"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICAL.2009.5262912"},{"year":"1989","author":"watkins","journal-title":"Learning from delayed rewards","key":"ref27"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1007\/s00170-019-04257-1"},{"year":"2011","author":"siegwart","journal-title":"Introduction to Autonomous Mobile Robots","key":"ref6"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1515\/amcs-2017-0053"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ACCESS.2019.2913916"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.22149\/teee.v2i2.96"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1007\/s10846-018-0805-9"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.23919\/ChiCC.2019.8866325"},{"key":"ref9","first-page":"1","article-title":"Backstepping control of wheeled mobile robots","author":"dumitrascu","year":"2011","journal-title":"Proc 15th Int Conf Syst Theory Control Comput"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1016\/j.biosystemseng.2016.11.004"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1016\/j.eswa.2019.06.066"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/IROS.2017.8202134"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/CCDC.2019.8832393"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/ACCESS.2019.2953326"},{"key":"ref23","first-page":"255","article-title":"Control of Mechatronic Systems","author":"szuster","year":"2017","journal-title":"Proc Intell Optim Adapt Control Mechatronic Syst"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1007\/1-4020-0611-X_580","article-title":"Markov decision processes","author":"white","year":"2001","journal-title":"Encyclopedia of Operations Research and Management Science"},{"key":"ref25","first-page":"1563","article-title":"Near-optimal regret bounds for reinforcement learning","volume":"11","author":"jaksch","year":"2010","journal-title":"J Mach Learn Res"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09171241.pdf?arnumber=9171241","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T22:57:24Z","timestamp":1667948244000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9171241\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3018026","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}