Over the last couple of chapters, we learned about the basics of ML—and, of course, specifically RL—using the Unity editor, and things were good. Unfortunately, the number of states in an RL problem can quickly exceed billions. The number of states in the game Go has been calculated to exceed the number of atoms in the observable universe, for instance. Now, dealing with these unfathomable numbers of states and doing the math for these types of problems isn't trivial. In fact, it is only just recently that we have been able to grapple with these numbers, thanks to the efforts of Google and others in releasing some powerful ML tools collectively called TensorFlow. TensorFlow is a math-execution library that has become the cornerstone of ML research because of the power it provides. Now, the preferred toolset when working...

#### Learn Unity ML-Agents ??? Fundamentals of Unity Machine Learning

#### Learn Unity ML-Agents ??? Fundamentals of Unity Machine Learning

#### Overview of this book

Unity Machine Learning agents allow researchers and developers to create games and simulations using the Unity Editor, which serves as an environment where intelligent agents can be trained with machine learning methods through a simple-to-use Python API.
This book takes you from the basics of Reinforcement and Q Learning to building Deep Recurrent Q-Network agents that cooperate or compete in a multi-agent ecosystem. You will start with the basics of Reinforcement Learning and how to apply it to problems. Then you will learn how to build self-learning advanced neural networks with Python and Keras/TensorFlow. From there you move o n to more advanced training scenarios where you will learn further innovative ways to train your network with A3C, imitation, and curriculum learning models. By the end of the book, you will have learned how to build more complex environments by building a cooperative and competitive multi-agent ecosystem.

Table of Contents (8 chapters)

Preface

Free Chapter

Introducing Machine Learning and ML-Agents

The Bandit and Reinforcement Learning

Deep Reinforcement Learning with Python

Going Deeper with Deep Learning

Playing the Game

Terrarium Revisited – A Multi-Agent Ecosystem

Other Books You May Enjoy

Customer Reviews