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

Direct policy search through policy gradient

The last method we're going to discuss doesn't employ a proxy to find the optimal policy, but rather looks for it directly. In this context, we always assume we're working with a stochastic environment where the transitions are not fully deterministic. For example, a robot can assign a high probability to a transition but, in order to increase the robustness, it has also to include a noise term that can lead the transition to a different state. Therefore, we need to include a transition probability .

Given this element, we can evaluate the overall probability of an entire sequence (that normally ends in a final state): S_k = (s₁, s₂, …, s_k). To do so, we need to define a parameterized policy ; therefore, the probability of S_k can be expressed as a conditional one: . The full expression requires us to explicitly separate the state transition component from the policy and to introduce the actions (which were implicit...