Applied Reinforcement Learning with Python: With Openai Gym, Tensorflow, and Keras

ISBN-13: 9781484251263 / Angielski / Miękka / 2019 / 168 str.

Taweh Beysolow

Opis

Beginning-Intermediate

Spis treści

Chapter 1:  Introduction to Reinforcement Learning

Chapter Goal: Inform the reader of the history of the field, its current applications, as well as generally discussing the outline of the text and what the reader can expect to learn 

No of pages 10

Sub -Topics

1. What is reinforcement learning? 

2. History of reinforcement learning 

3. Applications of reinforcement learning 

Chapter 2:  Reinforcement Learning Algorithms

Chapter Goal: Establishing an understanding with the reader about how reinforcement learning algorithms work and how they differ from basic ML/DL methods. Practical examples to be provided for this chapter

No of pages: 50 

Sub - Topics

1. Tabular solution methods

2. Approximate solution methods 

Chapter 3:  Q Learning 

Chapter Goal: In this chapter, readers will continue to build on their understanding of RL by solving problems in discrete action spaces 

No of pages : 40 

Sub - Topics:  

1. Deep Q networks

2. Double deep Q learning

Chapter 4: Reinforcement Learning Based Market Making 

Chapter Goal: In this chapter, we will focus on a financial based use case, specifically market making, in which we must buy and sell a financial instrument at any given price. We will apply a reinforcement learning approach to this data set and see how it performs over time 

No of pages: 50

Sub - Topics: 

1. Market making 

2. AWS/Google Cloud

3. Cron 

Chapter 5: Reinforcement Learning for Video Games 

Chapter Goal: In this chapter, we will focus on a more generalized use case of reinforcement learning in which we teach an algorithm to successfully play a game against computer based AI.  

No of pages: 50

Sub - Topics: 

1. Game background and data collection  

O autorze

Taweh Beysolow II is a data scientist and author currently based in the United States. He has a Bachelor of Science degree in economics from St. Johns University and a Master of Science in Applied Statistics from Fordham University. After successfully exiting the startup he co-founded, he now is a Director at Industry Capital, a San Francisco based Private Equity firm, where he helps lead the Cryptocurrency and Blockchain platforms.

Blurb

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 Keras
• Deploy and train reinforcement learning–based solutions via cloud resources
• Apply practical applications of reinforcement learning