Machine learning device, control device and machine learning method

A machine learning device that performs reinforcement learning in which a servo control device for controlling a motor is driven under a plurality of conditions and which optimizes a coefficient of at least one filter for attenuating at least one specific frequency component provided in the servo control device, the machine learning device comprising:

• a state information acquisition unit which acquires state information that includes a result of calculation of a frequency characteristic calculation device for calculating at least one of an input/output gain of the servo control device and a phase delay of an input and an output, the coefficient of the filter and the conditions;
• an action information output unit which outputs, to the filter, action information including adjustment information of the coefficient included in the state information;
• a reward output unit which individually determines evaluation values under the conditions based on the result of the calculation so as to output, as a reward, a value of a sum of the evaluation values;
• and
• a value function updating unit which updates an action value function based on a value of the reward output by the reward output unit, the state information and the action information.