Deep Learning in a Nutshell: Reinforcement Learning

This post is Part 4 of the Deep Learning in a Nutshell series, in which I'll dive into reinforcement learning, a type of machine learning in which agents take actions in an environment aimed at maximizing their cumulative reward. Deep Learning in a Nutshell posts offer a high-level overview of essential concepts in deep learning. The posts aim to provide an understanding of each concept rather than its mathematical and theoretical details. While mathematical terminology is sometimes necessary and can further understanding, these posts use analogies and images whenever possible to provide easily digestible bits that make up an intuitive overview of the field of deep learning. Previous posts covered core concepts in deep learning, training of deep learning networks and their history, and sequence learning. Remember how you learned to ride a bike? More than likely an adult stood or walked behind you and encouraged you to make the first moves on your bike, and helped you get going again when you stumbled or fell. But it is very difficult to explain to a child how to ride a bike, and even a good explanation makes little sense to someone who has never ridden before: you have to get the feel for it. So how did you learn to ride a bike if it could not be clearly explained?