Let us help you find the training program you are looking for.

If you can't find what you are looking for, contact us, we'll help you find it. We have over 800 training programs to choose from.

Learn Unity ML-Agents

  • Course Code: Artificial Intelligence - Learn Unity ML-Agents
  • Course Dates: Contact us to schedule.
  • Course Category: AI / Machine Learning Duration: 2 Days Audience: This course is geared for Python experienced developers, analysts or others who wish to Transform games into environments using machine learning and Deep learning with Tensorflow, Keras, and Unity

Course Snapshot 

  • Duration: 2 days 
  • Skill-level: Foundation-level Learn Unity ML-Agents skills for Intermediate skilled team members. This is not a basic class. 
  • Targeted Audience: This course is geared for Python experienced developers, analysts or others who wish to Transform games into environments using machine learning and Deep learning with Tensorflow, Keras, and Unity 
  • Hands-on Learning: This course is approximately 50% hands-on lab to 50% lecture ratio, combining engaging lecture, demos, group activities and discussions with machine-based student labs and exercises. Student machines are required. 
  • Delivery Format: This course is available for onsite private classroom presentation, or remote instructor led delivery, or CBT/WBT (by request). 
  • Customizable: This course may be tailored to target your specific training skills objectives, tools of choice and learning goals. 

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 course 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 course, you will have learned how to build more complex environments by building a cooperative and competitive multi-agent ecosystem. 

Working in a hands-on learning environment, led by our Unity ML-Agents instructor, students will learn about and explore: 

  • 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 

Topics Covered: This is a high-level list of topics covered in this course. Please see the detailed Agenda below 

  • 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 

Audience & Pre-Requisites 

This course is geared for attendees with Python skills who wish to Transform games into environments using machine learning and Deep learning with Tensorflow, Keras, and Unity 

Pre-Requisites:  Students should have  

  • Basic to Intermediate IT Skills. Attendees without a programming background like Python may view labs as follow along exercises or team with others to complete them. 
  • Good foundational mathematics or logic skills 
  • Basic Linux skills, including familiarity with command-line options such as ls, cd, cp, and su 

Course Agenda / Topics 

  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 
  1. 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 
  1. 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 
  1. 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 
  1. Playing the Game 
  • Playing the Game 
  • Multi-agent environments 
  • Adversarial self-play 
  • Decisions and On-Demand Decision Making 
  • Imitation learning 
  • Curriculum Learning 
  1. 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 
View All Courses

    Course Inquiry

    Fill in the details below and we will get back to you as quickly as we can.

    Interested in any of these related courses?