Applied Reinforcement Learning with Python

With OpenAI Gym, Tensorflow, and Keras

verfasst von: Taweh Beysolow II

Verlag: Apress

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

Delve into the world of reinforcement learning algorithms and apply them to different use-cases via Python. This book covers important topics such as policy gradients and Q learning, and utilizes frameworks such as Tensorflow, Keras, and OpenAI Gym.

Applied Reinforcement Learning with Python introduces you to the theory behind reinforcement learning (RL) algorithms and the code that will be used to implement them. You will take a guided tour through features of OpenAI Gym, from utilizing standard libraries to creating your own environments, then discover how to frame reinforcement learning problems so you can research, develop, and deploy RL-based solutions.

What You'll Learn

Implement reinforcement learning with Python Work with AI frameworks such as OpenAI Gym, Tensorflow, and KerasDeploy and train reinforcement learning–based solutions via cloud resourcesApply practical applications of reinforcement learning

Who This Book Is For

Data scientists, machine learning engineers and software engineers familiar with machine learning and deep learning concepts.

Inhaltsverzeichnis

Frontmatter

Chapter 1. Introduction to Reinforcement Learning

Abstract

To those returning from my previous books, Introduction to Deep Learning Using R and Applied Natural Learning Using Python, it is a pleasure to have you as readers again. To those who are new, welcome! Over the past year, there have continued to be an increased proliferation and development of deep learning packages and techniques that revolutionize various industries. One of the most exciting portions of this field, without a doubt, is Reinforcement Learning (RL). This itself is often what underlies a lot of generalized AI applications, such as software that learns to play video games or play chess. The benefit to reinforcement learning is that the agent can familiarize itself with a large range of tasks assuming that the problems can be modeled to a framework containing actions, an environment, an agent(s). Assuming that, the range of problems can be from solving simple games, to more complex 3-d games, to teaching self-driving cars how to pick up and drop off passengers in a variety of different places as well as teaching a robotic arm how to grasp objects and place them on top of a kitchen counter.

Taweh Beysolow II

Chapter 2. Reinforcement Learning Algorithms

Abstract

Readers should be aware that we will be utilizing various Deep Learning and Reinforcement Learning methods in this book. However, being that our focus will shift to discussing implementation and how these algorithms work in production settings, we must spend some time covering the algorithms themselves more granularly. As such, the focus of this chapter will be to walk the reader through several examples of Reinforcement Learning algorithms that are commonly applied and showing them in the context of utilizing Open AI gym with different problems.

Taweh Beysolow II

Chapter 3. Reinforcement Learning Algorithms: Q Learning and Its Variants

Abstract

With the preliminary discussion on policy gradients and Actor-Critic Models finished, we can now discuss alternative deep learning algorithms that readers might find useful. Specifically, we will discuss Q learning, Deep Q Learning, as well as Deep Deterministic Policy Gradients. Once we have covered these, we will be well versed enough to start dealing with more abstract problems that are more domain specific that will teach the user about how to approach reinforcement learning to different tasks.

Taweh Beysolow II

Chapter 4. Market Making via Reinforcement Learning

Abstract

Separate from just attacking some of the standard problems in reinforcement learning as they are found in many books as an example, it’s good to look at fields where the answers are either not as objective nor completely solved. One of the best examples of this in finance, specifically for reinforcement learning, is market making. We will discuss the discipline itself, present some baseline method that isn’t based on machine learning, and then test several reinforcement learning–based methods.

Taweh Beysolow II

Chapter 5. Custom OpenAI Reinforcement Learning Environments

Abstract

For our final chapter, we will be focusing on Open AI’s gym package, but more importantly trying to understand how we can create our own custom environments so we can tackle more than the typical use cases. Most of this chapter will focus around what I would suggest regarding programming practices for Open AI as well as recommendations on how I would generally write most of this software. Finally, after we have completed creating an environment, we will move on to focusing on solving the problem. For this instance, we will focus on trying to create and solve a new video game.

Taweh Beysolow II

Backmatter

Titel: Applied Reinforcement Learning with Python
verfasst von: Taweh Beysolow II
Verlag: Apress
Electronic ISBN: 978-1-4842-5127-0
Print ISBN: 978-1-4842-5126-3
DOI: https://doi.org/10.1007/978-1-4842-5127-0