The effect of selected variables on Q-learning during the control of asynchronous electric motor

THE EFFECT OF SELECTED VARIABLES ON Q-LEARNING DURINNG THE CONTROL 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. The paper is focused on presentation of random error effect of system variable observation, delay of interference action and response on jump torque onto convergence speed.

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. The paper is focused on presentation of random error effect of system variable observation, delay of interference action and response on jump torque onto convergence speed.

asynchronous motor, control, q-learning, pre-learning stage, tutorage stage

MARADA, T., BŘEZINA, T.,

2005

9. 5. 2005

Svratka, CZ

80-85918-93-5

Engineering Mechanics 2005

1

215

216

2