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


We started off this chapter by understanding TensorFlow and how it uses computational graphs. We learned that computation in TensorFlow is represented by a computational graph, which consists of several nodes and edges, where nodes are mathematical operations, such as addition and multiplication, and edges are tensors.

Next, we learned that variables are containers used to store values, and they are used as input to several other operations in a computational graph. We also learned that placeholders are like variables, where we only define the type and dimension but do not assign the values, and the values for the placeholders are fed at runtime. Moving forward, we learned about TensorBoard, which is TensorFlow's visualization tool and can be used to visualize a computational graph. We also explored eager execution, which is more Pythonic and allows rapid prototyping.

We understood that, unlike graph mode, where we need to construct a graph every time to perform...