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
Neural Networks with Keras Cookbook

You're reading from   Neural Networks with Keras Cookbook Over 70 recipes leveraging deep learning techniques across image, text, audio, and game bots

Arrow left icon
Product type Paperback
Published in Feb 2019
Publisher Packt
ISBN-13 9781789346640
Length 568 pages
Edition 1st Edition
Languages
Tools
Arrow right icon
Authors (2):
Arrow left icon
V Kishore Ayyadevara V Kishore Ayyadevara
Author Profile Icon V Kishore Ayyadevara
V Kishore Ayyadevara
Srinivas Pradeep Srinivas Pradeep
Author Profile Icon Srinivas Pradeep
Srinivas Pradeep
Arrow right icon
View More author details
Toc

Table of Contents (18) Chapters Close

Preface 1. Building a Feedforward Neural Network FREE CHAPTER 2. Building a Deep Feedforward Neural Network 3. Applications of Deep Feedforward Neural Networks 4. Building a Deep Convolutional Neural Network 5. Transfer Learning 6. Detecting and Localizing Objects in Images 7. Image Analysis Applications in Self-Driving Cars 8. Image Generation 9. Encoding Inputs 10. Text Analysis Using Word Vectors 11. Building a Recurrent Neural Network 12. Applications of a Many-to-One Architecture RNN 13. Sequence-to-Sequence Learning 14. End-to-End Learning 15. Audio Analysis 16. Reinforcement Learning 17. Other Books You May Enjoy

Deep Q-learning to play Space Invaders game

In the previous section, we used Deep Q-learning to play the Cart-Pole game. In this section, we will leverage Deep Q-learning to play Space Invaders, which is a more complex environment than Cart-Pole.

A sample screenshot of the Space Invaders game looks as follows:

source: https://gym.openai.com/envs/SpaceInvaders-v0/

The objective of this exercise is to maximize the score obtained in a single game.

Getting ready

The strategy that we'll adopt to build an agent that is able to maximize the score is as follows:

  • Initialize the environment of the Space Invaders-Atari2600 game.
  • Preprocess the image frame:
    • Remove pixels that do not necessarily impact the action prediction
      • For...
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