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


In this chapter, we've covered MAB problems, which is one-step reinforcement learning with many practical business applications. Despite its apparent simplicity, it is tricky to balance the exploration and exploitation in MAB problems, and any improvements in managing this trade-off comes with savings in costs and increases in revenue. We have introduced four approaches to this end: A/B/n testing, ε-greedy actions, action selection using upper confidence bounds and Thompson sampling. We implemented these approaches in an online advertising scenario and discussed their advantages and disadvantages.

So far, while making decisions, we have not considered any information about the situation in the environment. For example, we have not used any information about the users (e.g. location, age, previous behavior etc.) in the online advertising scenario that could be available to our decision-making algorithm. In the next chapter, you will learn about a more advanced...