Search icon CANCEL
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
Mastering TensorFlow 1.x

You're reading from   Mastering TensorFlow 1.x Advanced machine learning and deep learning concepts using TensorFlow 1.x and Keras

Arrow left icon
Product type Paperback
Published in Jan 2018
Publisher Packt
ISBN-13 9781788292061
Length 474 pages
Edition 1st Edition
Languages
Tools
Arrow right icon
Toc

Table of Contents (21) Chapters Close

Preface 1. TensorFlow 101 2. High-Level Libraries for TensorFlow FREE CHAPTER 3. Keras 101 4. Classical Machine Learning with TensorFlow 5. Neural Networks and MLP with TensorFlow and Keras 6. RNN with TensorFlow and Keras 7. RNN for Time Series Data with TensorFlow and Keras 8. RNN for Text Data with TensorFlow and Keras 9. CNN with TensorFlow and Keras 10. Autoencoder with TensorFlow and Keras 11. TensorFlow Models in Production with TF Serving 12. Transfer Learning and Pre-Trained Models 13. Deep Reinforcement Learning 14. Generative Adversarial Networks 15. Distributed Models with TensorFlow Clusters 16. TensorFlow Models on Mobile and Embedded Platforms 17. TensorFlow and Keras in R 18. Debugging TensorFlow Models 19. Tensor Processing Units
20. Other Books You May Enjoy

Deep Reinforcement Learning

Reinforcement learning is a form of learning in which a software agent observes the environment and takes actions so as to maximize its rewards from the environment, as depicted in the following diagram:

This metaphor can be used to represent real-life situations such as the following:

  • A stock trading agent observes the trade information, news, analysis, and other form information, and takes actions to buy or sell trades so as to maximize the reward in the form of short-term profit or long-term profit.
  • An insurance agent observes the information about the customer and then takes action to define the amount of insurance premium, so as to maximize the profit and minimize the risk.
  • A humanoid robot observes the environment and then takes action, such as walking, running, or picking up objects, so as to maximize the reward in terms of the goal achieved...
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 €18.99/month. Cancel anytime