Chapter 15. Reinforcement Learning
You may wonder, at this stage of the book, how robotics, gaming, and autonomous systems leverage machine learning. The answer lies in a field of AI known as reinforcement learning. For those with no familiarity with reinforcement learning, I highly recommend you read the seminal book on reinforcement learning by R. Sutton and A. Barto [11:1] if you are interested to know about its origin, purpose, and scientific foundation.
The first part of this chapter focuses on the Q-learning algorithm. The second part is dedicated to Learning Classifier Systems (LCS), which combine reinforcement learning techniques with evolutionary computing, introduced in the previous chapter. Learning classifiers are an interesting breed of algorithm that is not commonly included in literature dedicated to machine learning.
In this chapter, you will learn the following:
- Basic concepts behind reinforcement learning
- Detailed implementation of the Q-learning algorithm
- A simple...
