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

Learning DDPG, TD3, and SAC

In the previous chapter, we learned about interesting actor-critic methods, such as Advantage Actor-Critic (A2C) and Asynchronous Advantage Actor-Critic (A3C). In this chapter, we will learn several state-of-the-art actor-critic methods. We will start off the chapter by understanding one of the popular actor-critic methods called Deep Deterministic Policy Gradient (DDPG). DDPG is used only in continuous environments, that is, environments with a continuous action space. We will understand what DDPG is and how it works in detail. We will also learn the DDPG algorithm step by step.

Going forward, we will learn about the Twin Delayed Deep Deterministic Policy Gradient (TD3). TD3 is an improvement over the DDPG algorithm and includes several interesting features that solve the problems faced in DDPG. We will understand the key features of TD3 in detail and also look into the algorithm of TD3 step by step.

Finally, we will learn...