Reinforcement learning aims to create algorithms that can learn and adapt to environmental changes. This programming technique is based on the concept of receiving external stimuli depending on the algorithm choices. A correct choice will involve a premium, while an incorrect choice will lead to a penalty. The goal of system is to achieve the best possible result, of course. In this chapter, we dealt with the basics of reinforcement learning.

To begin with, we saw that the goal of learning with reinforcement is to create intelligent agents that are able to learn from their experience. So we analyzed the steps to follow to correctly apply a reinforcement learning algorithm. Later we explored the Agent-Environment interface. The entity that must achieve the goal is called an agent. The entity with which the agent must interact is called the environment, which corresponds to everything outside the agent.

To avoid load problems and computational difficulties, the Agent-Environment interaction is considered an MDP. An MDP is a stochastic control process. Then the discount factor concept was introduced. The discount factor can be modified during the learning process to highlight or not highlight particular actions or states. An optimal policy can cause the reinforcement obtained in performing a single action to be even low (or negative), provided that overall this leads to greater reinforcement.

In the central part of the chapter, were dedicated to the analysis of the most common reinforcement learning techniques. Q-learning, TD learning, and deep Q-learning networks were covered. Finally, we explored the OpenAI Gym libraries and tackled the analysis of a practical example of reinforcement learning.