A machine learning device that performs machine learning with respect to a changing unit configured to change a parameter of a control unit configured to control a servo motor and a compensation value of at least one of a position command and a torque command includes: a state information acquisition unit configured to acquire state information including the position command, a positional error, a combination of the parameter and the compensation value; an action information output unit configured to output action information including adjustment information of the combination of the parameter and the compensation value included in the state information; a reward output unit configured to output a reward value of reinforcement learning based on the positional error included in the state information; and a value function updating unit configured to update a value function based on the value of the reward, the state information, and the action information.