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

Asynchronous advantage actor-critic (A3C)

Asynchronous advantage actor-critic, hereinafter referred to as A3C, is one of the popular actor-critic algorithms. The main idea behind the asynchronous advantage actor-critic method is that it uses several agents for learning in parallel and aggregates their overall experience.

In A3C, we will have two types of networks, one is a global network (global agent), and the other is the worker network (worker agent). We will have many worker agents, each worker agent uses a different exploration policy, and they learn in their own copy of the environment and collect experience. Then, the experience obtained from these worker agents is aggregated and sent to the global agent. The global agent aggregates the learning.

Now that we have a very basic idea of how A3C works, let's go into more detail.

The three As

Before diving in, let's first learn what the three A's in A3C signify.

Asynchronous: Asynchronous implies...