Deep Reinforcement Learning with Python - Second Edition

13

TRPO, PPO, and ACKTR Methods

In this chapter, we will learn two interesting state-of-art policy gradient algorithms: trust region policy optimization and proximal policy optimization. Both of these algorithms act as an improvement to the policy gradient algorithm (REINFORCE with baseline) we learned in Chapter 10, Policy Gradient Method.

We begin the chapter by understanding the Trust Region Policy Optimization (TRPO) method and how it acts as an improvement to the policy gradient method. Later we will understand several essential math concepts that are required to understand TRPO. Following this, we will learn how to design and solve the TRPO objective function. At the end of the section, we will understand how the TRPO algorithm works step ...