Get Started with Actor Critic and Policy Gradient Methods
7 videos • 11,325 views • by Machine Learning with Phil Actor Critic and Policy Gradient methods serve as the sole approach to mastering deep reinforcement learning for problems with continuous action spaces. This is of particular interest to fields like robotics, where we are interested in controlling the motion of robotic controllers through applied voltages. In this series of tutorials, you will learn the fundamentals of how actor critic and policy gradient agents work, and be better prepared to move on to more advanced actor critic methods such as deep deterministic policy gradients (DDPG), asynchronous advantage actor critic (A3C), twin delayed deep deterministic policy gradients (TD3), and soft actor critic (SAC). You will write code in both the PyTorch and Tensorflow deep learning frameworks.