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

Playing Atari games with a DQN and its variants

Now, let's learn how to create a DQN to play Atari games with Stable Baselines. First, let's import the necessary modules:

from stable_baselines import DQN

Since we are dealing with Atari games, we can use a convolutional neural network instead of a vanilla neural network. So, we use CnnPolicy:

from stable_baselines.deepq.policies import CnnPolicy

We learned that we preprocess the game screen before feeding it to the agent. With Stable Baselines, we don't have to preprocess manually; instead, we can make use of the make_atari module, which takes care of preprocessing the game screen:

from stable_baselines.common.atari_wrappers import make_atari

Now, let's create an Atari game environment. Let's create the Ice Hockey game environment:

env = make_atari('IceHockeyNoFrameskip-v4')

Instantiate the agent:

agent = DQN(CnnPolicy, env, verbose=1)

Train the agent...