What you'll learn

Reinforcement learning is a powerful area of machine learning that involves agents learning by exploring their environment. In this course, Introduction to Reinforcement Learning, you’ll learn the basic concepts and elements of reinforcement learning. First, you’ll explore how to model the learning problem with Markov Decision Processes. Next, you’ll discover basic algorithms like Dynamic Programming and Monte Carlo methods, that allow an agent to learn from exploration. Finally, you’ll learn about more generally applicable methods like Temporal Difference Learning, Q-learning, and deep reinforcement learning. When you’re finished with this course, you’ll have the skills and knowledge of reinforcement learning and how it can be applied to a variety of machine learning problems.