In this chapter, you learned about the main algorithms in RL, Q-learning, policy gradients, and evolutionary strategies. You saw how these algorithms could be applied to trading and learned about some of the pitfalls of applying RL. You also saw the direction of current research and how you can benefit from this research today. At this point in the book, you are now equipped with a number of advanced machine learning algorithms, which are hopefully useful to you when developing machine learning models.

In the next chapter, we will discuss the practicalities of developing, debugging, and deploying machine learning systems. We will break out of the data-science sandbox and get our models into the real world.