1-5-4. Resources

As part of this course, we will recommend excerpts from this classic textbook on reinforcement learning. Note that all of the suggested readings are optional! Check out this GitHub repository to see Python implementations of most of the figures in the book. Before transitioning to the next lesson, you are encouraged to read Chapter 1 (especially 1.1-1.4) of … Read more

1-5-2. Applications

Optional Resources Read about TD-Gammon, one of the first successful applications of neural networks to reinforcement learning. Read about AlphaGo Zero, the state-of-the-art computer program that defeats professional human Go players. Learn about how reinforcement learning (RL) is used to play Atari games. Read about OpenAI’s bot that beat the world’s top players of Dota 2. Read about research used to teach humanoid … Read more

4 – Resources

In this course, you’ll learn about many classical algorithms in reinforcement learning. You may discover that some algorithms are initially harder to conceptualize than others. If at any point you’d like to have a conversation to deepen your understanding, we encourage you to start a thread in the slack channels. We at Udacity believe in … Read more

3 – The Setting

Throughout this course, we’ll concern ourselves with the idea of learning from interaction. In the field of reinforcement learning, we refer to the learner or decision maker as the agent. But I really like dogs, so we’ll instead, think of the agent as a small puppy born into the world without any understanding of how … Read more

2 – Applications

The applications of reinforcement learning are numerous and diverse. Ranging from self-driving cars to board games. For instance, one of the major breakthroughs in machine learning in the 90s was TD-Gammon. An algorithm that used RL to play Backgammon on par with the best Backgammon players at the time. This algorithm advanced the theory of … Read more

1 – Introduction

Let’s talk about the nature of learning. We are not born knowing much. Over the curse of our lifetimes, we slowly gain an understanding of the world through interaction. By interacting with the world, We learn about cause and effect or how the world responds to our actions. Once we have an understanding of how … Read more