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
Mastering Machine Learning Algorithms

You're reading from   Mastering Machine Learning Algorithms Expert techniques to implement popular machine learning algorithms and fine-tune your models

Arrow left icon
Product type Paperback
Published in May 2018
Publisher Packt
ISBN-13 9781788621113
Length 576 pages
Edition 1st Edition
Arrow right icon
Author (1):
Arrow left icon
Giuseppe Bonaccorso Giuseppe Bonaccorso
Author Profile Icon Giuseppe Bonaccorso
Giuseppe Bonaccorso
Arrow right icon
View More author details
Toc

Table of Contents (17) Chapters Close

Preface 1. Machine Learning Model Fundamentals FREE CHAPTER 2. Introduction to Semi-Supervised Learning 3. Graph-Based Semi-Supervised Learning 4. Bayesian Networks and Hidden Markov Models 5. EM Algorithm and Applications 6. Hebbian Learning and Self-Organizing Maps 7. Clustering Algorithms 8. Ensemble Learning 9. Neural Networks for Machine Learning 10. Advanced Neural Models 11. Autoencoders 12. Generative Adversarial Networks 13. Deep Belief Networks 14. Introduction to Reinforcement Learning 15. Advanced Policy Estimation Algorithms 16. Other Books You May Enjoy

TD(λ) algorithm

In the previous chapter, we introduced the temporal difference strategy, and we discussed a simple example called TD(0). In the case of TD(0), the discounted reward is approximated by using a one-step backup. Hence, if the agent performs an action at in the state st, and the transition to the state st+1 is observed, the approximation becomes the following:

If the task is episodic (as in many real-life scenarios) and has T(ei) steps, the complete backup for the episode ei is as follows:

The previous expression ends when the MDP process reaches an absorbing state; therefore, Rt is the actual value of the discounted reward. The difference between TD(0) and this choice is clear: in the first case, we can update the value function after each transition, whereas with a complete backup, we need to wait for the end of the episode. We can say that this method...

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