Welcome to the Deep Reinforcement Learning Nanodegree program. We’re so excited that you’ve joined us. I’m Alexis Cook, the curriculum lead for this program. I’ll be your guide through the Nanodegree. Your journey through the fascinating world of deep reinforcement learning will start at the very beginning. So we’ll begin by answering the question, what is deep reinforcement learning exactly? Well, reinforcement learning is ultimately about building code that can learn to perform complex tasks by itself, and deep reinforcement learning refers to approaches where the knowledge is represented with a deep neural network. For example, maybe you’ve heard about AlphaGo Zero, the computer program that’s able to beat world champions at the ancient Chinese game of Go. AlphaGo Zero learned for itself how to play without being told any rules of the game. It just starts playing and then based on whether it has won or lost, it can assess how good it’s strategy is. Reinforcement learning helps AlphaGo Zero to learn from this gameplay experience so that it’s able to learn from those wins and losses, to propose gradually better strategies and eventually master the game. This trial and error approach can also be extended to other domains. For instance, to teach a robot to walk or train a chatbot how to have better conversations. Companies such as Uber and Google are actively testing reinforcement learning algorithms and their self-driving cars, and Amazon currently uses reinforcement learning to make their warehouses more efficient. The possibilities are truly endless and It’s widely considered the technology that brings us closer than never to artificial general intelligence. While we’re still quite far from developing a super-human computer that matches human intelligence, the algorithms you’ll learn in this course are logical first step in this direction and that’s why we built this program, so that you’re able to master this fascinating and potentially world changing technology. We can’t wait to see where this journey takes you.