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

Distributed Distributional DDPG

D4PG, which stands for Distributed Distributional Deep Deterministic Policy Gradient, is one of the most interesting policy gradient algorithms. We can make a guess about how D4PG works just by its name. As the name suggests, D4PG is basically a combination of deep deterministic policy gradient (DDPG) and distributional reinforcement learning, and it works in a distributed fashion. Confused? Let's go deeper and understand how D4PG works in detail.

To understand how D4PG works, it is highly recommended to revise the DDPG algorithm we covered in Chapter 12, Learning DDPG, TD3, and SAC. We learned that DDPG is an actor critic method where the actor tries to learn the policy while the critic tries to evaluate the policy produced by the actor using the Q function. The critic uses the deep Q network for estimating the Q function and the actor uses the policy network for computing the policy. Thus, the actor performs an action while the critic gives...