Book Image

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

Book Image

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.

Related Content you might be interested in

Current Title:

Small book image
Learn Unity ML-Agents ??? Fundamentals of Unity Machine Learning
Jun, 2018 | 204 pages
Small book image
Hands-On Deep Learning for Games
Micheal Lanham
Mar, 2019 | 392 pages
Small book image
Hands-On Reinforcement Learning for Games
Micheal Lanham
Jan, 2020 | 432 pages
Small book image
Learn ARCore - Fundamentals of Google ARCore
Micheal Lanham
Mar, 2018 | 274 pages
Table of Contents (8 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Get in touch
Free Chapter
1
Introducing Machine Learning and ML-Agents
Introducing Machine Learning and ML-Agents
Machine Learning
ML-Agents
Running a sample
Creating an environment
Academy, Agent, and Brain
Summary
2
The Bandit and Reinforcement Learning
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
3
Deep Reinforcement Learning with Python
Deep Reinforcement Learning with Python
Installing Python and tools
ML-Agents external brains
Neural network foundations
Deep Q-learning
Proximal policy optimization
Exercises
Summary
4
Going Deeper with Deep Learning
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
5
Playing the Game
Playing the Game
Multi-agent environments
Adversarial self-play
Decisions and On-Demand Decision Making
Imitation learning
Curriculum Learning
Exercises
Summary
6
Terrarium Revisited – A Multi-Agent Ecosystem
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
7
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think

Partial observability, memory, and recurrent networks

One major difference between the Hallway and GridWorld examples is their perception of state, or observation. We already know that the GridWorld agent used visual observations, but we never really got into what state input the Hallway agent used. As it turns out, the Hallway agent collects observations of state in a different manner. It is important for us to understand the difference, so open up Unity and go through the following exercise:

  1. Make sure the Hallway example scene is loaded. Check back to the previous exercise if you need help.
  2. Locate the Agent object in the Hierarchy window. You can use the search bar at the top of the window to find it quicker.
  3. Find the Hallway Agent component/script in the Inspector window.
  4. Click the target icon beside the component and select Edit Script.... This will open your previously set...
Previous Section
End of Section 5
Next Section