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

Modeling routing problems

Routing problems are among the most challenging and well-studied in combinatorial optimization. In fact, there are quite a few of researchers who dedicated their entire careers to this area. Recently, RL approaches to routing problems have emerged as an alternative to the traditional operations research methods. We start with a rather sophisticated routing problem, which is about the pick-up and delivery of online meal orders. The RL modeling to this problem, on the other hand, will not be that complex. We will later extend our discussion to more advanced RL models in line of the recent literature in this area.

Pick-up and delivery of online meal orders

Consider a gig driver (our agent) who works for an online platform, similar to Uber Eats or Grubhub, to pick up orders from restaurants and deliver to customers. The goal of the driver is to collect as much tips as possible by delivering many expensive orders. Here are some more details about this environment...