Deep Reinforcement Learning with Python - Second Edition

10

Policy Gradient Method

In the previous chapters, we learned how to use value-based reinforcement learning algorithms to compute the optimal policy. That is, we learned that with value-based methods, we compute the optimal Q function iteratively and from the optimal Q function, we extract the optimal policy. In this chapter, we will learn about policy-based methods, where we can compute the optimal policy without having to compute the optimal Q function.

We will start the chapter by looking at the disadvantages of computing a policy from the Q function, and then we will learn how policy-based methods learn the optimal policy directly without computing the Q function. Next, we will examine one of the most popular policy-based methods, called ...