Processing device having selectible difficulty levels with intuitive learning capability

A processing device and a method of providing learning capability thereto are provided. One of a plurality of processor actions is selected based on an action probability distribution comprising a plurality of probability values corresponding to the plurality of processor actions. The plurality of processor actions are associated with a plurality of different difficulty levels. An action performed by a user is identified, an outcome of selected processor action relative to the identified user action is determined, and the action probability distribution is updated based on the outcome and the difficulty level of the selected processor action.