TY - GEN
T1 - Deep reinforcement learning based neuro-control for a two-dimensional magnetic positioning system
AU - Bejar, Eduardo
AU - Moran, Antonio
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/6/13
Y1 - 2018/6/13
N2 - 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.
AB - 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.
KW - deep deterministic policy gradient (DDPG) algorithm
KW - magnetic positioning system
KW - Q-learning
KW - reinforcement learning
UR - http://www.scopus.com/inward/record.url?scp=85049894841&partnerID=8YFLogxK
U2 - 10.1109/ICCAR.2018.8384682
DO - 10.1109/ICCAR.2018.8384682
M3 - Conference contribution
AN - SCOPUS:85049894841
T3 - Proceedings - 2018 4th International Conference on Control, Automation and Robotics, ICCAR 2018
SP - 268
EP - 273
BT - Proceedings - 2018 4th International Conference on Control, Automation and Robotics, ICCAR 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 4th International Conference on Control, Automation and Robotics, ICCAR 2018
Y2 - 20 April 2018 through 23 April 2018
ER -