Applied reinforcement learning with Python : with OpenAI Gym, Tensorflow and Keras / Taweh Beysolow II.
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 introdu...
Saved in:
| Online Access: |
Full Text (via Skillsoft) |
|---|---|
| Main Author: | |
| Format: | Electronic eBook |
| Language: | English |
| Published: |
[Berkely, California] :
Apress,
[2019]
|
| Subjects: |
Table of Contents:
- Chapter 1: Introduction to Reinforcement LearningChapter 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 10Sub -Topics1. What is reinforcement learning? 2. History of reinforcement learning 3. Applications of reinforcement learning Chapter 2: Reinforcement Learning AlgorithmsChapter 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 methods2. 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 networks2. 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: 50Sub
- Topics: 1. Market making 2. AWS/Google Cloud3. 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: 50Sub
- Topics: 1. Game background and data collection.