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

Introducing eager execution

Eager execution in TensorFlow is more Pythonic and allows rapid prototyping. Unlike graph mode, where we need to construct a graph every time we want to perform any operation, eager execution follows the imperative programming paradigm, where any operation can be performed immediately, without having to create a graph, just like we do in Python. Hence, with eager execution, we can say goodbye to sessions and placeholders. It also makes the debugging process easier with an immediate runtime error, unlike graph mode. For instance, in graph mode, to compute anything, we run the session. As shown in the following code, to evaluate the value of z, we have to run the TensorFlow session:

x = tf.constant(11)
y = tf.constant(11)
z = x*y
with tf.Session() as sess:
    print(sess.run(z))

With eager execution, we don't need to create a session; we can simply compute z, just like we do in Python. In order to enable eager execution, just call...