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

Bringing the action in: Markov decision process

A Markov reward process allowed us to model and study a Markov chain with rewards. Of course, our ultimate goal is to control such a system to achieve the maximum rewards. Now, we incorporate decisions into the MRP.


A Markov decision process (MDP) is simply a Markov reward process with decisions affecting transition probabilities and potentially the rewards.


An MDP is characterized by a tuple , where we have a finite set of actions, , on top of MRP.

MDP is the mathematical framework behind RL. So, this is time to remember the RL diagram that we introduced in Chapter 1, Introduction to Reinforcement Learning:

Figure 4.8 – Markov decision process diagram

Our goal in MDP is to find a policy that maximizes expected cumulative reward. A policy simply tells which action(s) to take for a given state. In other words, it is a mapping from states to actions. More formally, a policy...