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 the chapter by understanding the DDPG algorithm. We learned that DDPG is an actor-critic algorithm where the actor estimates the policy using policy gradient and the critic evaluates the policy produced by the actor using the Q function. We learned how DDPG uses a deterministic policy and how it is used in environments with a continuous action space.

Later, we looked into the actor and critic components of DDPG in detail and understood how they work, before finally learning about the DDPG algorithm.

Moving on, we learned about the twin delayed DDPG, which is the successor to DDPG and constitutes an improvement to the DDPG algorithm. We learned the key features of TD3, including clipped double Q learning, delayed policy updates, and target policy smoothing, in detail and finally, we looked into the TD3 algorithm.

At the end of the chapter, we learned about the SAC algorithm. We learned that, unlike DDPG and TD3, the SAC method uses a stochastic policy...