What you'll learn

Actor-critic methods and advantage estimation is a powerful but advanced method of training ML models that can solve complex, time-based problems that simple DNN cannot. In this course, Actor-critic Methods and Advantage Estimation, you’ll learn to understand, train and implement these models. First, you’ll explore the actor-critic method, learning how it works and how it varies from other RL methods. Next, you’ll discover advantage estimation and how it is applied in training more consistent, balanced policies. Finally, you’ll learn how to implement actor-critic method in Python and compare the results of different RL techniques. When you’re finished with this course, you’ll have the skills and knowledge of actor-critic method and advantage estimation needed to develop, maintain, and improve advanced RL models.