Nowadays, most computers are based on a symbolic elaboration. The problem is first encoded in a set of variables and then processed using an explicit algorithm that, for each possible input of the problem, offers an adequate output. However, there are problems in which resolution by an explicit algorithm is inefficient or even unnatural, for example, a speech recognizer; tackling this kind of problem with the classic approach is inefficient. This and other similar problems, such as autonomous navigation of a robot or voice assistance in performing an operation, are part of a very diverse set of problems that can be addressed directly through solutions based on reinforcement learning.
Reinforcement learning is based on a psychology theory, elaborated after a series of experiments performed on animals. Defining a goal to be achieved, reinforcement learning...