In this chapter, we are going to introduce the fundamental concepts of Reinforcement Learning (RL), which is a set of approaches that allows an agent to learn how to behave in an unknown environment, thanks to the rewards that are provided after each possible action. RL has been studied for decades, but it has reached a very high maturity level in the last few years when it became possible to employ deep learning models together with standard (and often simple) algorithms in order to solve extremely complex problems (such as learning how to play an Atari game perfectly).
In particular, we will discuss:
- The concepts of environment, agent, policy, and reward
- The concept of the Markov Decision Process ...
