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

Chapter 2: Multi-Armed Bandits

When you log on to your favorite social media app, chances are you see one of the many versions of the app that are tested at that time. When you visit a website, the ads displayed to you are tailored to your profile. In many online shopping platforms, the prices are determined dynamically. Do you know what all these have in common? They are often modeled as multi-armed bandit (MAB) problems to identify optimal decisions. A MAB problem is a form of reinforcement learning (RL), where the agent makes decisions in a problem horizon that consists of a single step. Therefore, the goal is to maximize only the immediate reward, and there are no consequences considered for any subsequent steps. While this is a simplification over multi-step RL, the agent must still deal with a fundamental trade-off of RL: Exploration of new actions that could possibly lead to higher rewards, versus exploitation of the actions that are known to be decent. A wide range of business...