Practical Artificial Intelligence: Machine Learning, Bots, and Agent Solutions Using C#

© Arnaldo Pérez Castaño 2018

Arnaldo Pérez CastañoPractical Artificial Intelligencehttps://doi.org/10.1007/978-1-4842-3357-3_17

17. Reinforcement Learning

Arnaldo Pérez Castaño¹ 

(1)

Havana, Cuba

 

So far in this book we have examined both supervised and unsupervised learning algorithms. In this chapter, we will discuss reinforcement learning algorithms. Remember: In supervised learning we had a dataset composed of samples (x, y) where x was usually a vector of features of some object (house, plane, person, city, and so on) and y was the correct classification of x. Thus, supervised learning was the process of learning or approximating a function from tabular data. This approach more closely resembles the way computers analyze data than the way humans ...