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

Playing Atari games using DQN

The Atari 2600 is a popular video game console from a game company called Atari. The Atari game console provides several popular games, such as Pong, Space Invaders, Ms. Pac-Man, Breakout, Centipede, and many more. In this section, we will learn how to build a DQN for playing the Atari games. First, let's explore the architecture of the DQN for playing the Atari games.

Architecture of the DQN

In the Atari environment, the image of the game screen is the state of the environment. So, we just feed the image of the game screen as input to the DQN and it returns the Q values of all the actions in the state. Since we are dealing with images, instead of using a vanilla deep neural network for approximating the Q value, we can use a convolutional neural network (CNN) since it is very effective for handling images.

Thus, now our DQN is a CNN. We feed the image of the game screen (the game state) as input to the CNN, and it outputs the Q...