Book Image

Mastering Reinforcement Learning with Python

By : Enes Bilgin
Book Image

Mastering Reinforcement Learning with Python

By: Enes Bilgin

Overview of this book

Reinforcement learning (RL) is a field of artificial intelligence (AI) used for creating self-learning autonomous agents. Building on a strong theoretical foundation, this book takes a practical approach and uses examples inspired by real-world industry problems to teach you about state-of-the-art RL. Starting with bandit problems, Markov decision processes, and dynamic programming, the book provides an in-depth review of the classical RL techniques, such as Monte Carlo methods and temporal-difference learning. After that, you will learn about deep Q-learning, policy gradient algorithms, actor-critic methods, model-based methods, and multi-agent reinforcement learning. Then, you'll be introduced to some of the key approaches behind the most successful RL implementations, such as domain randomization and curiosity-driven learning. As you advance, you’ll explore many novel algorithms with advanced implementations using modern Python libraries such as TensorFlow and Ray’s RLlib package. You’ll also find out how to implement RL in areas such as robotics, supply chain management, marketing, finance, smart cities, and cybersecurity while assessing the trade-offs between different approaches and avoiding common pitfalls. By the end of this book, you’ll have mastered how to train and deploy your own RL agents for solving RL problems.
Table of Contents (24 chapters)
Section 1: Reinforcement Learning Foundations
Section 2: Deep Reinforcement Learning
Section 3: Advanced Topics in RL
Section 4: Applications of RL

A/B/n testing

One of the most common exploration strategies is what is called A/B testing, which is a method to determine which one of the two alternatives (of online products, pages, ads etc.) performs better. In this type of testing, the users are randomly split into two groups to try different alternatives. At the end of the testing period, the results are compared to choose the best alternative, which is then used in production for the rest of the problem horizon. In our case, we have more than two ad versions. So, we will implement what is called A/B/n testing.

We will use A/B/n testing as our baseline strategy for the comparison with the more advanced methods that we will introduce afterwards. Before going into the implementation, we need to define some notation that we will use throughout the chapter.


Throughout the implementations of various algorithms, we will need to keep track of some quantities related to a particular action (ad chosen for display) ....