Deep reinforcement learning based neuro-control for a two-dimensional magnetic positioning system
Authors:
- 1 April 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 268-273
Abstract
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.Keywords
This publication has 8 references indexed in Scilit:
- Three-link planar arm control using reinforcement learning2017
- Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates2017
- Deep reinforcement learning approaches for process control2017
- Deep reinforcement learning for partial differential equation control2017
- A New Design of a Submicropositioner Utilizing Electromagnetic Actuators and Flexure MechanismIEEE Transactions on Industrial Electronics, 2009
- Electromagnetic Actuator Control: A Linear Parameter-Varying (LPV) ApproachIEEE Industrial Electronics Magazine, 2007
- Multi-Axis Maglev Nanopositioner for Precision Manufacturing and Manipulation ApplicationsIEEE Transactions on Industry Applications, 2005
- On the Theory of the Brownian MotionPhysical Review B, 1930