This book provides a comprehensive introduction to reinforcement learning with mathematical theory and practical examples from quantitative finance using the TensorFlow library. It covers training neural networks, deep learning networks, reinforcement learning theory, and recent algorithms, with hands-on examples using TensorFlow. It is designed for data scientists, machine learning engineers, and Python programmers interested in applying reinforcement learning to solve quantitative-finance problems.

Format: Paperback / softback
Length: 423 pages
Publication date: 27 December 2022
Publisher: APress

Reinforcement Learning for Finance

Reinforcement Learning for Finance is a comprehensive guide that introduces readers to the world of reinforcement learning with a focus on its applications in quantitative finance. The book begins by providing an overview of neural network training methods, which are crucial for implementing reinforcement learning algorithms. It then delves into two types of neural networks commonly used in reinforcement learning: convolutional neural networks (CNNs) and recurrent neural networks (RNNs).

The book goes on to discuss reinforcement learning theory, which forms the foundation of these algorithms. It covers key concepts such as the Markov decision process, value function, policy, and policy gradients, explaining their mathematical formulations and learning algorithms. The book provides practical examples using the TensorFlow Python library, showcasing recent reinforcement learning algorithms such as double deep-Q networks, twin-delayed deep deterministic policy gradients, and generative adversarial networks.

In addition to theoretical discussions, the book offers a hands-on approach to TensorFlow programming. It covers essential concepts such as variables, graphs, automatic differentiation, layers, models, and loss functions, enabling readers to build and train their own reinforcement learning models. The book is designed for data scientists, machine learning engineers, and Python programmers who are interested in applying reinforcement learning to solve problems in quantitative finance.

By the end of this book, readers will have a solid understanding of reinforcement learning with deep q and generative adversarial networks using the TensorFlow library. They will be equipped with the skills and knowledge necessary to apply these algorithms to real-world financial problems and gain a competitive edge in the field.

Weight: 670g
Dimension: 235 x 155 (mm)
ISBN-13: 9781484288344
Edition number: 1st ed.