MACHINE LEARNING METHOD, MACHINE LEARNING DEVICE, MACHINE LEARNING PROGRAM, COMMUNICATION METHOD, AND KNEADING DEVICE

摘要

This machine learning method includes acquiring a state variable including at least one first evaluation parameter relating to performance evaluation of kneaded matter and at least one kneading condition, calculating a reward with regard to a decision result of at least one kneading condition on the basis of the state variable, updating a function for deciding the at least one kneading condition from the state variable on the basis of the reward, and deciding a kneading condition where the reward obtained is greatest by repeating updating of the function. The at least one first evaluation parameter includes at least one of a physical property and a shape property regarding the kneaded matter.