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

1 (3)

Buy this Book

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

1 (3)

Buy this Book

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.

Preface

Who this book is for

What this book covers

To get the most out of this book

Get in touch

Free Chapter

Introducing Machine Learning and ML-Agents

Machine Learning

ML-Agents

Running a sample

Creating an environment

Academy, Agent, and Brain

Summary

The Bandit and Reinforcement Learning

Reinforcement Learning

Contextual bandits and state

Exploration and exploitation

MDP and the Bellman equation

Q-Learning and connected agents

Exercises

Summary

Deep Reinforcement Learning with Python

Installing Python and tools

ML-Agents external brains

Neural network foundations

Deep Q-learning

Proximal policy optimization

Exercises

Summary

Going Deeper with Deep Learning

Agent training problems

Convolutional neural networks

Experience replay

Partial observability, memory, and recurrent networks

Asynchronous actor – critic training

Exercises

Summary

Playing the Game

Multi-agent environments

Adversarial self-play

Decisions and On-Demand Decision Making

Imitation learning

Curriculum Learning

Exercises

Summary

Terrarium Revisited – A Multi-Agent Ecosystem

What was/is Terrarium?

Building the Agent ecosystem

Basic Terrarium – Plants and Herbivores

Carnivore: the hunter

Next steps

Exercises

Summary

Other Books You May Enjoy

Leave a review - let other readers know what you think

Customer Reviews

1 (3)

5 star

4 star

3 star

2 star

1 star

100%

Adversarial self-play

The last example we looked at is best defined as a competitive multi-agent training scenario where the agents are learning by competing against each other to collect bananas or freeze other agents out. In this section, we will look at another similar form of training that pits agent vs. agent using an inverse reward scheme called Adversarial self-play. Inverse rewards are used to punish an opposing agent when a competing agent receives as reward. Let's see what this looks like in the Unity ML-Agents Soccer (football) example by following this exercise:

Open up Unity to the SoccerTwos scene located in the Assets/ML-Agents/Examples/Soccer/Scenes folder.
Run the scene and use the WASD keys to play all four agents. Stop the scene when you are done having fun.
Expand the Academy object in the Hierarchy window.
Select the StrikerBrain and switch it to External...

Your notes and bookmarks

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

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

Overview of this book

Delete Bookmark