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

Case Study – The MAB Problem

So far in the previous chapters, we have learned the fundamental concepts of reinforcement learning and also several interesting reinforcement learning algorithms. We learned about a model-based method called dynamic programming and a model-free method called the Monte Carlo method, and then we learned about the temporal difference method, which combines the advantages of dynamic programming and the Monte Carlo method.

In this chapter, we will learn about one of the classic problems in reinforcement learning called the multi-armed bandit (MAB) problem. We start the chapter by understanding the MAB problem, and then we will learn about several exploration strategies, called epsilon-greedy, softmax exploration, upper confidence bound, and Thompson sampling, for solving the MAB problem. Following this, we will learn how a MAB is useful in real-world use cases.

Moving forward, we will understand how to find the best advertisement banner...