12. Evolutionary Strategies for RL
In this chapter, we will be identifying the limitations of gradient-based methods and the motivation for evolutionary strategies. We will break down the components of genetic algorithms and implement them in Reinforcement Learning (RL). By the end of this chapter, you will be able to combine evolutionary strategies with traditional machine learning methods, specifically in the selection of neural network hyperparameters, and also identify the limitations of these evolutionary methods.
In the previous chapter, we looked at various policy-based methods and their advantages. In this chapter, we are going to learn about gradient-free methods, namely genetic algorithms; develop these ...