Book Image

The Reinforcement Learning Workshop

By : Alessandro Palmas, Emanuele Ghelfi, Dr. Alexandra Galina Petre, Mayur Kulkarni, Anand N.S., Quan Nguyen, Aritra Sen, Anthony So, Saikat Basak
Book Image

The Reinforcement Learning Workshop

By: Alessandro Palmas, Emanuele Ghelfi, Dr. Alexandra Galina Petre, Mayur Kulkarni, Anand N.S., Quan Nguyen, Aritra Sen, Anthony So, Saikat Basak

Overview of this book

Various intelligent applications such as video games, inventory management software, warehouse robots, and translation tools use reinforcement learning (RL) to make decisions and perform actions that maximize the probability of the desired outcome. This book will help you to get to grips with the techniques and the algorithms for implementing RL in your machine learning models. Starting with an introduction to RL, youÔÇÖll be guided through different RL environments and frameworks. YouÔÇÖll learn how to implement your own custom environments and use OpenAI baselines to run RL algorithms. Once youÔÇÖve explored classic RL techniques such as Dynamic Programming, Monte Carlo, and TD Learning, youÔÇÖll understand when to apply the different deep learning methods in RL and advance to deep Q-learning. The book will even help you understand the different stages of machine-based problem-solving by using DARQN on a popular video game Breakout. Finally, youÔÇÖll find out when to use a policy-based method to tackle an RL problem. By the end of The Reinforcement Learning Workshop, youÔÇÖll be equipped with the knowledge and skills needed to solve challenging problems using reinforcement learning.
Table of Contents (14 chapters)
Preface
Free Chapter
2
2. Markov Decision Processes and Bellman Equations

Summary

In this chapter, we were introduced to practical deep learning with TensorFlow 2 and Keras, their key features and applications, and how they work together. We became familiar with the differences between low- and high-level APIs, as well as how to leverage the most advanced modules to ease the creation of deep models. Then, we discussed how to implement a deep neural network with TensorFlow and addressed some major topics: from model creation, training, validation, and testing, we highlighted the most important aspects to consider so as to avoid pitfalls. We saw how to build different types of deep learning models, such as fully connected, convolutional, and recurrent neural networks, via the Keras API. We solved a regression task and a classification problem, which gave us hands-on experience with this. We learned how to leverage TensorBoard to visualize many different training trends regarding metrics and model parameters. Finally, we built and trained a model that is able...