Component supply device and machine learning device

A machine learning device that learns an operation parameters for a vibration operation, by which an arrangement and a posture of components placed on a tray are changed, of the tray in a component supply device for supplying the components placed on the tray, the machine learning device comprising:

• a state observation unit that observes vibration operation parameter data representing the operation parameters for the vibration operation, component arrangement data representing an arrangement and a posture of the components on the tray, and component kind data representing a kind of the components, as a state variable representing a current state of an environment;
• a determination data acquisition unit that acquires determination data representing a suitability determination result of the vibration operation, the suitability determination result representing efficiency in supply of the components, and
• a learning unit that learns the operation parameters for the vibration operation, the component arrangement data, and the component kind data while associating the operation parameters for the vibration operation with the component arrangement data and the component kind data, by using the state variable and the determination data.