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
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Hands-On Q-Learning with Python

You're reading from   Hands-On Q-Learning with Python Practical Q-learning with OpenAI Gym, Keras, and TensorFlow

Arrow left icon
Product type Paperback
Published in Apr 2019
Publisher Packt
ISBN-13 9781789345803
Length 212 pages
Edition 1st Edition
Languages
Tools
Arrow right icon
Author (1):
Arrow left icon
Nazia Habib Nazia Habib
Author Profile Icon Nazia Habib
Nazia Habib
Arrow right icon
View More author details
Toc

Table of Contents (14) Chapters Close

Preface 1. Section 1: Q-Learning: A Roadmap FREE CHAPTER
2. Brushing Up on Reinforcement Learning Concepts 3. Getting Started with the Q-Learning Algorithm 4. Setting Up Your First Environment with OpenAI Gym 5. Teaching a Smartcab to Drive Using Q-Learning 6. Section 2: Building and Optimizing Q-Learning Agents
7. Building Q-Networks with TensorFlow 8. Digging Deeper into Deep Q-Networks with Keras and TensorFlow 9. Section 3: Advanced Q-Learning Challenges with Keras, TensorFlow, and OpenAI Gym
10. Decoupling Exploration and Exploitation in Multi-Armed Bandits 11. Further Q-Learning Research and Future Projects 12. Assessments 13. Other Books You May Enjoy

Chapter 5, Building Q-Networks with TensorFlow

  1. An extensional definition is given in terms of examples. An intensional definition is a dictionary definition, given in terms of a high-level description.
  2. Feedforward is the process by which values of individual nodes in a network are calculated, and the values are then multiplied by network weights and used as inputs to other nodes in the next layer of the network.
  3. The weights in a neural network are used to calculate values to be propagated through the network. They function as coefficients and are updated through backpropagation to improve the accuracy of the network.
  1. Gradient descent is an optimization function that adjusts its parameters iteratively to minimize error. It is used in backpropagation to adjust the weights on a neural network to correctly approximate the desired function.
  2. Backpropagation is used to train neural...
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