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

Chapter 15: Supply Chain Management

Effective supply chain management is a challenge for many businesses, yet it is key to their profitability and competitiveness. The difficulty in this area comes from a complex set of dynamics affecting supply and demand, business constraints around handling them, and a great uncertainty all along. Reinforcement learning provides us with a key set of capabilities to address such sequential decision-making problems.

In this chapter, we particularly focus on two important problems: Inventory and routing optimization. For the former, we go into the details of creating the environment, understanding the variance in the environment, and hyperparameter tuning to effectively solve it using reinforcement learning. For the latter, we describe a realistic vehicle routing problem of a gig driver working to deliver online meal orders. We then proceed to show why conventional neural networks are limiting while solving problems in varying sizes, and how pointer...