Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Advanced Deep Learning with TensorFlow 2 and Keras

You're reading from   Advanced Deep Learning with TensorFlow 2 and Keras Apply DL, GANs, VAEs, deep RL, unsupervised learning, object detection and segmentation, and more

Arrow left icon
Product type Paperback
Published in Feb 2020
Publisher Packt
ISBN-13 9781838821654
Length 512 pages
Edition 2nd Edition
Languages
Tools
Arrow right icon
Author (1):
Arrow left icon
Rowel Atienza Rowel Atienza
Author Profile Icon Rowel Atienza
Rowel Atienza
Arrow right icon
View More author details
Toc

Table of Contents (16) Chapters Close

Preface 1. Introducing Advanced Deep Learning with Keras 2. Deep Neural Networks FREE CHAPTER 3. Autoencoders 4. Generative Adversarial Networks (GANs) 5. Improved GANs 6. Disentangled Representation GANs 7. Cross-Domain GANs 8. Variational Autoencoders (VAEs) 9. Deep Reinforcement Learning 10. Policy Gradient Methods 11. Object Detection 12. Semantic Segmentation 13. Unsupervised Learning Using Mutual Information 14. Other Books You May Enjoy
15. Index

6. Deep Q-Network (DQN)

Using the Q-table to implement Q-learning is fine in small discrete environments. However, when the environment has numerous states or is continuous, as in most cases, a Q-table is not feasible or practical. For example, if we are observing a state made of four continuous variables, the size of the table is infinite. Even if we attempt to discretize the four variables into 1,000 values each, the total number of rows in the table is a staggering 10004 = 1e12. Even after training, the table is sparse – most of the cells in this table are zero.

A solution to this problem is called DQN [2], which uses a deep neural network to approximate the Q-table, as shown in Figure 9.6.1. There are two approaches to building the Q-network:

  • The input is the state-action pair, and the prediction is the Q value
  • The input is the state, and the prediction is the Q value for each action

The first option is not optimal since the network will...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $19.99/month. Cancel anytime
Banner background image