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

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 the policy gradient. We will first take a broad overview of the policy gradient algorithm, and then we will learn more about it in detail.

Going forward, we will also learn how to derive the policy gradient step by step and examine...