Reinforcement Learning for Engineers, Part 3: Policies and Learning Algorithms

This video provides an introduction to the algorithms that reside within the agent. We’ll cover why we use neural networks to represent functions and why you may have to set up two neural networks in a powerful family of methods called actor-critic.

Reinforcement Learning by Sutton and Barto: http://bit.ly/2HAYbb4
RL course by David Silver: https://youtu.be/2pWv7GOvuf0
3B1B videos on neural networks: http://bit.ly/2WRmaq9
Michael Neilson’s blog: Follow up: http://bit.ly/2WMUtP1
A nice write up on policy gradient algorithms and the policy gradient theorem by Lilian Weng: http://bit.ly/2WP6bIS
A paper motivating the usefulness of deep neural networks: http://bit.ly/2WI591o
Brendan Fortuner’s blog: http://bit.ly/2WUmRy

Part 1: What Is Reinforcement Learning?

Part 2: Understanding the Environment and Rewards

Part 4: The Walking Robot Problem

Part 5: Overcoming the Practical Challenges