Deep reinforcement learning based neuro-control for a two-dimensional magnetic positioning system

Eduardo Bejar, Antonio Moran

Producción científica: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

14 Citas (Scopus)

Resumen

This paper presents a control scheme based on deep reinforcement learning for a two-dimensional positioning system with electromagnetic actuators. Two neuro-controllers are trained and used for controlling the X-Y position of an object. The neuro-controllers learning approach is based on the actor-critic architecture and the deep deterministic policy gradient (DDPG) algorithm using the Q-learning method. The performance of the control system is verified for different setpoints and working conditions.

Idioma originalInglés
Título de la publicación alojadaProceedings - 2018 4th International Conference on Control, Automation and Robotics, ICCAR 2018
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas268-273
Número de páginas6
ISBN (versión digital)9781538663387
DOI
EstadoPublicada - 13 jun. 2018
Evento4th International Conference on Control, Automation and Robotics, ICCAR 2018 - Auckland, Nueva Zelanda
Duración: 20 abr. 201823 abr. 2018

Serie de la publicación

NombreProceedings - 2018 4th International Conference on Control, Automation and Robotics, ICCAR 2018

Conferencia

Conferencia4th International Conference on Control, Automation and Robotics, ICCAR 2018
País/TerritorioNueva Zelanda
CiudadAuckland
Período20/04/1823/04/18

Huella

Profundice en los temas de investigación de 'Deep reinforcement learning based neuro-control for a two-dimensional magnetic positioning system'. En conjunto forman una huella única.

Citar esto