You're reading from Mastering Machine Learning Algorithms Expert techniques for implementing popular machine learning algorithms, fine-tuning your models, and understanding how they work

Product type Paperback

Published in Jan 2020

Publisher Packt

ISBN-13 9781838820299

Length 798 pages

Edition 2nd Edition

Languages

Python

Tools

Keras

Concepts

Machine Learning

Authors (2):

Giuseppe Bonaccorso

View More author details

Table of Contents (28) Chapters

Preface

1. Machine Learning Model Fundamentals

2. Loss Functions and Regularization FREE CHAPTER

3. Introduction to Semi-Supervised Learning

4. Advanced Semi-Supervised Classification

5. Graph-Based Semi-Supervised Learning

6. Clustering and Unsupervised Models

7. Advanced Clustering and Unsupervised Models

8. Clustering and Unsupervised Models for Marketing

9. Generalized Linear Models and Regression

10. Introduction to Time-Series Analysis

11. Bayesian Networks and Hidden Markov Models

12. The EM Algorithm

13. Component Analysis and Dimensionality Reduction

14. Hebbian Learning

15. Fundamentals of Ensemble Learning

16. Advanced Boosting Algorithms

17. Modeling Neural Networks

18. Optimizing Neural Networks

19. Deep Convolutional Networks

20. Recurrent Neural Networks

21. Autoencoders

22. Introduction to Generative Adversarial Networks

23. Deep Belief Networks

24. Introduction to Reinforcement Learning

25. Advanced Policy Estimation Algorithms

26. Other Books You May Enjoy

27. Index

Value iteration

An alternative approach to policy iteration is provided by the value iteration algorithm. The main assumption is based on the empirical observation that the policy evaluation step converges rather quickly and it's reasonable to stop the process after a fixed number of steps (normally 1). In fact, policy iteration can be thought of as a game where the first player tries to find the correct values considering a stable policy, while the other player creates a new policy that is greedy with respect to the new values.

Clearly, the second step compromises the validity of the previous evaluation, forcing the first player to repeat the process. However, as the Bellman equation uses a single fixed point, the algorithm converges to a solution characterized by the fact that the policy doesn't change anymore and, consequently, the evaluation becomes stable. This process can be simplified by removing the policy improvement step and continuing the...