Machine learning apparatus for determining operation condition of precooling operation or preheating operation of air conditioner

A machine learning apparatus for determining an operation condition of a precooling operation or preheating operation of an air conditioner, the machine learning apparatus comprising:

• a controller including a computer, the controller being configured to
• execute an absence control while a user is absent, the absence control including at least one of the precooling operation or the preheating operation;
• acquire, as state variables, room temperature data at a time of the precooling operation or preheating operation, set temperature data, and outside air temperature data;
• learn the operation condition of the precooling operation or preheating operation based on the state variables and a reward, the reward is based on a room temperature at an end time of the precooling operation or preheating operation, a set temperature, and an electric energy required until the end time of the precooling operation or preheating operation;
• at the end time of the precooling operation or preheating operation, the controller being further configured to
• increase the reward if a difference between the room temperature and the set temperature is smaller than a first predetermined value and decrease the reward if the difference is equal to or larger than the first predetermined value, or
• increase the reward if the electric energy is smaller than a second predetermined value and decrease the reward if the electric energy is equal to or larger than a second predetermined value.