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)
1
Section 1: Reinforcement Learning Foundations
7
Section 2: Deep Reinforcement Learning
12
Section 3: Advanced Topics in RL
17
Section 4: Applications of RL

Case study: Online advertising

Consider a company that wants to advertise a product on various websites through digital banners, aiming to attract visitors to the product landing page. Among multiple alternatives, the advertiser company wants to find out which banner is the most effective and has the maximum click-through rate (CTR), which is defined as the total number of clicks an ad receives divided by the total number of impressions (number of times it is shown).

Every time a banner is about to be shown on a website, it is the advertiser's algorithm that chooses the banner (for example, through an API provided by the advertiser to the website) and observes whether the impression has resulted in a click or not. This is a great use case for a MAB model, which could boost the clicks and product sales. What we want the MAB model to do is to identify the ad that performs the best as early as possible, display it more, and write off the ad(s) that is(are) a clear loser(s) as...