Stanovení optimálního rastru Q-funkce pro řízení asynchronního elektromotoru

Determination of Q-function Optimum Grid for Control Task of Asynchronous Electric Motor

conference paper

Czech

Asynchronous electric motor control task can be successfully solved using reinforcement learning based method called Q-learning. The main problem to solve is the convergence speed. Two-phase Q-learning can be used to speed up the learning process. Efficient prelearning phase uses mathematical model and next phase using for tutorage real system. This method can increase learning speed significantly. When the table is used as Q-function approximation, the learning speed and precision of found controllers depend highly on the Q-function table grid properties. The paper is focused on finding the optimal division of grid.

Asynchronous electric motor control task can be successfully solved using reinforcement learning based method called Q-learning. The main problem to solve is the convergence speed. Two-phase Q-learning can be used to speed up the learning process. Efficient prelearning phase uses mathematical model and next phase using for tutorage real system. This method can increase learning speed significantly. When the table is used as Q-function approximation, the learning speed and precision of found controllers depend highly on the Q-function table grid properties. The paper is focused on finding the optimal division of grid.

Asynchronous electromotor, Q-learning, Control, PID

MARADA, T., BŘEZINA, T., SINGULE, V.

2004

24. 5. 2004

Slovak University of Technology Bratislava, Faculty of Mechanical Engineering CA MECHATRONICS

Bratislav, SK

80-227-2064-X

Proceedings of the 7th International Symposium "Topical Questions of Teaching Mechatronics"

71

75

5