Book Image

Deep Reinforcement Learning with Python - Second Edition

By : Sudharsan Ravichandiran
Book Image

Deep Reinforcement Learning with Python - Second Edition

By: Sudharsan Ravichandiran

Overview of this book

With significant enhancements in the quality and quantity of algorithms in recent years, this second edition of Hands-On Reinforcement Learning with Python has been revamped into an example-rich guide to learning state-of-the-art reinforcement learning (RL) and deep RL algorithms with TensorFlow 2 and the OpenAI Gym toolkit. In addition to exploring RL basics and foundational concepts such as Bellman equation, Markov decision processes, and dynamic programming algorithms, this second edition dives deep into the full spectrum of value-based, policy-based, and actor-critic RL methods. It explores state-of-the-art algorithms such as DQN, TRPO, PPO and ACKTR, DDPG, TD3, and SAC in depth, demystifying the underlying math and demonstrating implementations through simple code examples. The book has several new chapters dedicated to new RL techniques, including distributional RL, imitation learning, inverse RL, and meta RL. You will learn to leverage stable baselines, an improvement of OpenAI’s baseline library, to effortlessly implement popular RL algorithms. The book concludes with an overview of promising approaches such as meta-learning and imagination augmented agents in research. By the end, you will become skilled in effectively employing RL and deep RL in your real-world projects.
Table of Contents (22 chapters)
Other Books You May Enjoy

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 by step.

Moving on, we will learn about Proximal Policy Optimization (PPO). We will understand how PPO works and how it acts as an improvement to the TRPO algorithm in detail. We will also learn two types of PPO algorithm called PPO...