Table of Contents

Introduction to Reinforcement Learning

Markov Decision Processes and Bellman Equations

Deep Learning in Practice with TensorFlow 2

Getting Started with OpenAI and TensorFlow for Reinforcement Learning

Dynamic Programming

Monte Carlo Methods

Temporal Difference Learning

The Multi-Armed Bandit Problem

What Is Deep Q Learning?

Playing an Atari Game with Deep Recurrent Q Networks

Policy-Based Methods for Reinforcement Learning

Evolutionary Strategies for RL

About the Author

Alessandro Palmas has more than 7 years of proven expertise in software development for advanced scientific applications and complex software systems. Emanuele Ghelfi is a computer science and machine learning engineer. Dr. Alexandra Galina Petre is a machine learning and data science expert. Mayur Kulkarni works in the machine learning research team at Microsoft. Anand N.S. has a strong hands-on track record of working on applications for artificial intelligence. Quan Nguyen is a programmer with a special interest in artificial intelligence. Aritra Sen currently works as a data scientist in Ericsson. Anthony So is an outstanding leader with more than 13 years of experience. Saikat Basak is a data scientist and a passionate programmer.