Engineering Mechanics

Proceedings Vol. 10 (2004)

ENGINEERING MECHANICS 2004

Copyright © 2004 Institute of Thermomechanics, Academy of Sciences of the Czech Republic, Prague

 

Marada T., Březina T., Singule V.
pages 177 - +7p., full text

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.

Text and facts may be copied and used freely, but credit should be given to these Proceedings.

All papers were reviewed by members of the scientific committee.