Learn Unity ML-Agents : fundamentals of Unity machine learning : incorporate new powerful ML algorithms such as deep reinforcement learning for games / Michael Lanham.

Format:

Book

Author/Creator:

Lanham, Micheal, author.

Language:

English

Subjects (All):

Unity (Electronic resource).

Video games--Programming.

Video games.

Machine learning.

Application software--Development.

Application software.

Physical Description:

1 online resource (197 pages) : illustrations

Edition:

1st edition

Other Title:

Learn Unity Machine Learning-Agents

Place of Publication:

Birmingham ; Mumbai : Packt, 2018.

System Details:

text file

Summary:

Transform games into environments using machine learning and Deep learning with Tensorflow, Keras, and Unity About This Book Learn how to apply core machine learning concepts to your games with Unity Learn the Fundamentals of Reinforcement Learning and Q-Learning and apply them to your games Learn How to build multiple asynchronous agents and run them in a training scenario Who This Book Is For This book is intended for developers with an interest in using Machine learning algorithms to develop better games and simulations with Unity. The reader will be required to have a working knowledge of C# and a basic understanding of Python. What You Will Learn Develop Reinforcement and Deep Reinforcement Learning for games. Understand complex and advanced concepts of reinforcement learning and neural networks Explore various training strategies for cooperative and competitive agent development Adapt the basic script components of Academy, Agent, and Brain to be used with Q Learning. Enhance the Q Learning model with improved training strategies such as Greedy-Epsilon exploration Implement a simple NN with Keras and use it as an external brain in Unity Understand how to add LTSM blocks to an existing DQN Build multiple asynchronous agents and run them in a training scenario In Detail 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. Style and approach This book focuses on the foundations of ML, RL and DL for building agents in a game or simulation

Contents:

Cover

Title Page

Copyright and Credits

Dedication

Packt Upsell

Contributors

Table of Contents

Preface

Chapter 1: Introducing Machine Learning and ML-Agents

Machine Learning

Training models

A Machine Learning example

ML uses in gaming

ML-Agents

Running a sample

Setting the agent Brain

Creating an environment

Renaming the scripts

Academy, Agent, and Brain

Setting up the Academy

Setting up the Agent

Setting up the Brain

Exercises

Summary

Chapter 2: The Bandit and Reinforcement Learning

Reinforcement Learning

Configuring the Agent

Contextual bandits and state

Building the contextual bandits

Creating the ContextualDecision script

Updating the Agent

Exploration and exploitation

Making decisions with SimpleDecision

MDP and the Bellman equation

Q-Learning and connected agents

Looking at the Q-Learning ConnectedDecision script

Chapter 3: Deep Reinforcement Learning with Python

Installing Python and tools

Installation

Mac/Linux installation

Windows installation

Docker installation

GPU installation

Testing the install

ML-Agents external brains

Running the environment

Neural network foundations

But what does it do?

Deep Q-learning

Building the deep network

Training the model

Exploring the tensor

Proximal policy optimization

Implementing PPO

Understanding training statistics with TensorBoard

Chapter 4: Going Deeper with Deep Learning

Agent training problems

When training goes wrong

Fixing sparse rewards

Fixing the observation of state

Convolutional neural networks

Experience replay

Building on experience

Partial observability, memory, and recurrent networks

Partial observability

Memory and recurrent networks.

Asynchronous actor - critic training

Multiple asynchronous agent training

Chapter 5: Playing the Game

Multi-agent environments

Adversarial self-play

Using internal brains

Using trained brains internally

Decisions and On-Demand Decision Making

The Bouncing Banana

Imitation learning

Setting up a cloning behavior trainer

Curriculum Learning

Chapter 6: Terrarium Revisited - A Multi-Agent Ecosystem

What was/is Terrarium?

Building the Agent ecosystem

Importing Unity assets

Building the environment

Basic Terrarium - Plants and Herbivores

Herbivores to the rescue

Building the herbivore

Training the herbivore

Carnivore: the hunter

Building the carnivore

Training the carnivore

Next steps

Other Books You May Enjoy

Index.

Notes:

Description based on print version record.

ISBN:

9781789131864

1789131863

OCLC:

1045010181