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

Starting with Markov chains

We start this chapter with Markov chains, which do not involve any decision-making. They only model a special type of stochastic processes that are governed by some internal transition dynamics. Therefore, we don't talk about an agent yet. Understanding how Markov chains work will allow us to lay the foundation for MDPs that we will cover later.

Stochastic processes with Markov property

We already defined the state as the set information that completely describes the situation an environment is in. If the next state that the environment will transition into only depends on the current state, not the past, we say that the process has the Markov property. This is named after the Russian mathematician Andrey Markov.

Imagine a broken robot that randomly moves in a grid world. At any given step, the robot goes up, down, left and right with 0.2, 0.3, 0.25 and 0.25 probability, respectively. This is depicted in Figure 4.1, as follows: