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)
18
Other Books You May Enjoy
19
Index

Deep Q Network and Its Variants

In this chapter, let's get started with one of the most popular Deep Reinforcement Learning (DRL) algorithms called Deep Q Network (DQN). Understanding DQN is very important as many of the state-of-the-art DRL algorithms are based on DQN. The DQN algorithm was first proposed by researchers at Google's DeepMind in 2013 in the paper Playing Atari with Deep Reinforcement Learning. They described the DQN architecture and explained why it was so effective at playing Atari games with human-level accuracy. We begin the chapter by learning what exactly a deep Q network is, and how it is used in reinforcement learning. Next, we will deep dive into the algorithm of DQN. Then we will learn how to implement DQN to play Atari games.

After learning about DQN, we will cover several variants of DQN, such as double DQN, DQN with prioritized experience replay, dueling DQN, and the deep recurrent Q network in detail.

In this chapter, we...