Book Image

Mastering Machine Learning Algorithms. - Second Edition

By : Giuseppe Bonaccorso
Book Image

Mastering Machine Learning Algorithms. - Second Edition

By: Giuseppe Bonaccorso

Overview of this book

Mastering Machine Learning Algorithms, Second Edition helps you harness the real power of machine learning algorithms in order to implement smarter ways of meeting today's overwhelming data needs. This newly updated and revised guide will help you master algorithms used widely in semi-supervised learning, reinforcement learning, supervised learning, and unsupervised learning domains. You will use all the modern libraries from the Python ecosystem – including NumPy and Keras – to extract features from varied complexities of data. Ranging from Bayesian models to the Markov chain Monte Carlo algorithm to Hidden Markov models, this machine learning book teaches you how to extract features from your dataset, perform complex dimensionality reduction, and train supervised and semi-supervised models by making use of Python-based libraries such as scikit-learn. You will also discover practical applications for complex techniques such as maximum likelihood estimation, Hebbian learning, and ensemble learning, and how to use TensorFlow 2.x to train effective deep neural networks. By the end of this book, you will be ready to implement and solve end-to-end machine learning problems and use case scenarios.
Table of Contents (28 chapters)
Other Books You May Enjoy

Advanced Policy Estimation Algorithms

In this chapter, we'll complete our exploration of the world of Reinforcement Learning (RL), focusing our attention on complex algorithms that can be employed to solve difficult problems. The topic of RL is extremely large, and we couldn't cover it in its entirety even if we dedicated an entire book to it; this chapter is instead based on many practical examples that you can use as a basis to work on more complex scenarios.

The topics that will be discussed in this chapter are:

  • The TD() algorithm
  • Actor-Critic TD(0)
  • Q-learning, including a simple visual input and a neural network
  • Direct policy search through policy gradient

We can now start analyzing the natural extension of TD(0) algorithm, which helps take into account a longer sequence of transitions, obtaining a more accurate estimation of the value function.