Reinforcement Learning for Engineers, Part 4: The Walking Robot Problem

This video shows how to use the reinforcement learning workflow to get a bipedal robot to walk. It also looks at how to modify the default example to make it look more like how one would set up a traditional control problem by adding a reference signal. It will also consider how an RL-equipped agent can replace parts of a traditional control system rather than an end-to-end design.  Finally, some of the limitations of this design will be shown.

Deep Reinforcement Learning for Walking Robots: https://bit.ly/2WGPpfx You can find the example model used in this video in the MATLAB Central File Exchange: http://bit.ly/2HBxe79 Reinforcement Learning by Sutton and Barto: http://bit.ly/2HAYbb4 Reinforcement Learning course by David Silver: https://youtu.be/2pWv7GOvuf0

Part 1: What Is Reinforcement Learning?

Part 2: Understanding the Environment and Rewards

Part 3: Policies and Learning Algorithms

Part 5: Overcoming the Practical Challenges