Mastering Reinforcement Learning with Python

Build next-generation, self-learning models using reinforcement learning techniques and best practices

Enes Bilgin

• Publisher: Packt Publishing
• Year: 2020
• ISBN:
  9781838648497
• Edition: 1
• Topic: Computer Science
• Subtopic: Artificial Intelligence (AI) & Semantics
• Index: Computer Science

Get hands-on experience in creating state-of-the-art reinforcement learning agents using TensorFlow and RLlib to solve complex real-world business and industry problems with the help of expert tips and best practices

Key Features

• Understand how large-scale state-of-the-art RL algorithms and approaches work
• Apply RL to solve complex problems in marketing, robotics, supply chain, finance, cybersecurity, and more
• Explore tips and best practices from experts that will enable you to overcome real-world RL challenges

Book Description

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.

What you will learn

• Model and solve complex sequential decision-making problems using RL
• Develop a solid understanding of how state-of-the-art RL methods work
• Use Python and TensorFlow to code RL algorithms from scratch
• Parallelize and scale up your RL implementations using Ray's RLlib package
• Get in-depth knowledge of a wide variety of RL topics
• Understand the trade-offs between different RL approaches
• Discover and address the challenges of implementing RL in the real world

Who this book is for

This book is for expert machine learning practitioners and researchers looking to focus on hands-on reinforcement learning with Python by implementing advanced deep reinforcement learning concepts in real-world projects. Reinforcement learning experts who want to advance their knowledge to tackle large-scale and complex sequential decision-making problems will also find this book useful. Working knowledge of Python programming and deep learning along with prior experience in reinforcement learning is required.

Section 1: Reinforcement Learning Foundations

This part covers the necessary background of Reinforcement Learning (RL) to prepare you for the advanced material in later chapters. This includes definitions, mathematical foundations, and an overview of RL solution methodology.

This section contains the following chapters:

• Chapter 1, Introduction to Reinforcement Learning
• Chapter 2, Multi-Armed Bandits
• Chapter 3, Contextual Bandits
• Chapter 4, Makings of a Markov Decision Process
• Chapter 5, Solving the Reinforcement Learning Problem

Chapter 1: Introduction to Reinforcement Learning

Reinforcement Learning (RL) aims to create Artificial Intelligence (AI) agents that can make decisions in complex and uncertain environments, with the goal of maximizing their long-term benefit. These agents learn how to do it through interacting with their environments, which mimics the way we as humans learn from experience. As such, RL has an incredibly broad and adaptable set of applications, with the potential to disrupt and revolutionize global industries.

This book will give you an advanced level understanding of this field. We will go deeper into the theory behind the algorithms you may already know, and cover state-of-the art RL. Moreover, this is a practical book. You will see examples inspired by real-world industry problems and learn expert tips along the way. By its conclusion, you will be able to model and solve your own sequential decision-making problems using Python.

So, let's start our journey with refreshing your mind on RL concepts and get you set up for the advanced material upcoming in the following chapters. Specifically, this chapter covers:

• Why reinforcement learning?
• The three paradigms of ML
• RL application areas and success stories
• Elements of a RL problem
• Setting up your RL environment

Why reinforcement learning?

Creating intelligent machines that make decisions at or superior to human level is a dream of many scientist and engineers, and one which is gradually becoming closer to reality. In the seven decades since the Turing test, AI research and development has been on a roller coaster. The expectations were very high initially: In the 1960s, for example, Herbert Simon (who later received the Nobel Prize in Economics) predicted that machines would be capable of doing any work humans can do within twenty years. It was this excitement that attracted big government and corporate funding flowing into AI research, only to be followed by big disappointments and a period called the "AI winter." Decades later, thanks to the incredible developments in computing, data, and algorithms, humankind is again very excited, more than ever before, in its pursuit of the AI dream.

Note

If you're not familiar with Alan Turing's instrumental work on the foundations of AI in 1950, it's worth learning more about the Turing Test here: https://youtu.be/3wLqsRLvV-c

The AI dream is certainly one of grandiosity. After all, the potential in intelligent autonomous systems is enormous. Think about how we are limited in terms of specialist medical doctors in the world. It takes years and significant intellectual and financial resources to educate them, which many countries don't have at sufficient levels. In addition, even after years of education, it is nearly impossible for a specialist to stay up-to-date with all of the scientific developments in her field, learn from the outcomes of the tens of thousands of treatments around the world, and effectively incorporate all this knowledge into practice.

Conversely, an AI model could process and learn from all this data and combine it with a rich set of information about a patient (medical history, lab results, presenting symptoms, health profile) to make diagnosis and suggest treatments. Such a model could serve even in the most rural parts of the world (as far as an internet connection and computer are available) and direct the local health personnel about the treatment. No doubt that it would revolutionize international healthcare and improve the lives of millions of people.

Note

AI is already transforming the healthcare industry. In a recent article, Google published results from an AI system surpassing human experts in breast cancer prediction using mammography readings (McKinney et al. 2020). Microsoft is collaborating with one of India's largest healthcare providers to detect cardiac illnesses using AI (Agrawal, 2018). IBM Watson for Clinical Trial Matching uses natural language processing to recommend potential treatments for patients from medical databases (https://youtu.be/grDWR7hMQQQ).

On our quest to develop AI systems that are at or superior to human level, which is -sometimes controversially- called Artificial General Intelligence (AGI), it makes sense to develop a model that can learn from its own experience - without necessarily needing a supervisor. RL is the computational framework that enables us to create such intelligent agents. To better understand the value of RL, it is important to compare it with the other ML paradigms, which we'll look into next.

The three paradigms of ML

RL is a separate paradigm in Machine Learning (ML) along supervised learning (SL) and unsupervised learning (UL). It goes beyond what the other two paradigms involve – perception, classification, regression and clustering – and makes decisions. Importantly however, RL utilizes the supervised and unsupervised ML methods in doing so. Therefore, RL is a distinct yet a closely related field to supervised and UL, and it's important to have a grasp of them.

Supervised learning

SL is about learning a mathematical function that maps a set of inputs to the corresponding outputs/labels as accurately as possible. The idea is that we don't know the dynamics of the process that generates the output, but we try to figure it out using the data coming out of it. Consider the following examples:

• An image recognition model that classifies the objects on the camera of a self-driving car as pedestrian, stop sign, truck
• A forecasting model that predicts the customer demand of a product for a particular holiday season using past sales data.

It is extremely difficult to come up with the precise rules to visually differentiate objects, or what factors lead to customers demanding a product. Therefore, SL models infer them from labeled data. Here are some key points about how it works:

• During training, models learn from ground truth labels/output provided by a supervisor (which could be a human expert or a process),
• During inference, models make predictions about what the output might be given the input,
• Models use function approximators to represent the dynamics of the processes that generate the outputs.

Unsupervised learning

UL algorithms identify patterns in data that were previously unknown. While using such models, we might have an idea of what to expect as a result, but we don't supply the models with labels. For example:

• Identifying homogenous segments on an image provided by the camera of a self-driving car. The model is likely to separate the sky, road and buildings based on the textures on the image.
• Clustering weekly sales data into 3 groups based on sales volume. The output is likely to be weeks with low, medium, and high sales volume.

As you can tell, this is quite different than how SL works, namely:

• UL models don't know what the ground truth is, and there is no label to map the input to. They just identify the different patterns in the data. Even after doing so, for example, the model would not be aware that it separated sky from road, or a holiday week from a regular week.
• During inference, the model would cluster the input into one of the groups it had identified, again, without knowing what that group represents.
• Function approximators, such as neural networks, are used in some UL algorithms, bu...