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

What is a MAB?

A MAB problem is all about identifying the best action among a set of actions available to an agent through trial and error, such as figuring out the best look for a website among some alternatives, or the best ad banner to run for a product. We will focus on the more common variant of MABs where there are discrete actions available to the agent, also known as -armed bandit problem.

Let's define the problem in more detail through the example it got its name from.

Problem definition

The MAB problem is named after the case of a gambler who needs to choose a slot machine (bandit) to play in a row of machines:

  • When the lever of a machine is pulled, it gives a random reward coming from a probability distribution specific to that machine.
  • Although the machines look identical, their reward probability distributions are different.

The gambler is trying to maximize his total reward. So, in each turn, he needs to decide whether to play the...