DEEP Q-LEARNING IN ROBOTICS: A PATH PLANNING ALTERNATIVE

dc.contributorGerardo Flores
dc.creatorGesem Mejia
dc.date2022
dc.date.accessioned2023-07-21T15:15:57Z
dc.date.available2023-07-21T15:15:57Z
dc.identifierhttp://cio.repositorioinstitucional.mx/jspui/handle/1002/1266
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/7726020
dc.description"Robotics is a particularly challenging domain for any learning algorithm. Using Deep Q Learning, this work goes from simple robotic systems that learn how to balance a pendulum to more complex ones like performing path planning tasks that allow mobile robots to learn new behaviors in an initially unknown environment. Experiments on simulated environments have been presented and results have proved to be suitable for real world tests."
dc.formatapplication/pdf
dc.languageeng
dc.relationcitation:Gudiño Mejía, (2022). "Deep Q-Learning in robotics: A path planning alternative". Tesis de Maestría Interinstitucional en Ciencia y Tecnología. Centro de Investigaciones en Óptica, A.C. León, Guanajuato. 52 pp.
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rightshttp://creativecommons.org/licenses/by-nc-nd/4.0
dc.subjectinfo:eu-repo/classification/Autor/Reinforcement Learning
dc.subjectinfo:eu-repo/classification/Autor/Path planning
dc.subjectinfo:eu-repo/classification/Autor/Robotics
dc.subjectinfo:eu-repo/classification/Autor/Deep learning
dc.subjectinfo:eu-repo/classification/Autor/Drones
dc.subjectinfo:eu-repo/classification/Autor/Q-learning
dc.subjectinfo:eu-repo/classification/cti/7
dc.subjectinfo:eu-repo/classification/cti/33
dc.subjectinfo:eu-repo/classification/cti/3399
dc.subjectinfo:eu-repo/classification/cti/339999
dc.subjectinfo:eu-repo/classification/cti/339999
dc.titleDEEP Q-LEARNING IN ROBOTICS: A PATH PLANNING ALTERNATIVE
dc.typeinfo:eu-repo/semantics/masterThesis
dc.typeinfo:eu-repo/semantics/acceptedVersion
dc.coverageLeón, Guanajuato
dc.audiencelibrarians
dc.audiencestudents
dc.audienceresearchers
dc.audiencegeneralPublic


Este ítem pertenece a la siguiente institución