Pole-balancing experiments
In this chapter, we continued with experiments related to the classic problems of computer science in the field of reinforcement learning. We started with a discussion of how to implement an avoidance control optimization method using the NEAT algorithm, allowing us to balance a cart-pole apparatus (or an inverted pendulum). We began with a single pole-balancing system and provided all the necessary equations of motion that allow us to numerically approximate real-world physical apparatus.
We learned how specific control actions could be applied to the cart-pole apparatus in the form of the bang-bang controller. The bang-bang controller is a unique form of control system that is designed to apply a series of actions ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access