Build a self-driving car without a car: ML problem-solving with a game engine

Description

Whether you’re a data scientist who wants to test a research problem without building costly and complicated real-world rigs, a self-driving car engineer who wants to test your AI logic in a constrained virtual world, or a data scientist who needs to solve a thorny real-world problem without a production environment, simulation-driven ML problem solving with a game engine might be the solution to your problems. Imagine you’re building a high-volume, expensive, robot-driven warehouse. Your pick, place, and packing robots need to get to the right place quickly, find the right item, and sort it to the right place without colliding with each other, the shelves, or people. But you don’t have any robots yet, and you need to start writing, or training, the behavior.

A game engine is a controlled, self-contained spatial, physical environment that (can) closely replicate (enough of) the real world (to be useful). Paris Buttfield-Addison, Tim Nugent, and Mars Geldard explore how you can use game engines to explore and solve problems—such as the aforementioned warehouse—in a simulated environment without building costly and complicated real-world rigs. They detail how to solve AI and ML problems using the Unity game engine and TensorFlow for Python. Learn how you could use a game engine to train, explore, and manipulate intelligent agents that learn, explore, and help you understand a problem space.

Game engines are a great place to explore ML and AI. They’re wonderful constrained problem spaces, tiny little ecosystems for you to explore a problem in. Here you can learn to use them, even though you’re not a game developer.

Outline:

In this tutorial, you’ll look at

• How video game engines are a perfect environment to constrain a problem and train an agent
• How easy it is to get started using the Unity engine and Google’s TensorFlow for Python
• How to build up a model, and use it in the engine, to explore a particular idea or problem
• Proximal policy optimization (PPO) for generic but useful machine learning
• Deep reinforcement learning and how it lets you explore and study complex behaviors

Specifically, Paris, Tim, and Mars will

• Teach you the very basics of the Unity game engine
• Explore how to design and set up a scene in Unity for both training and use of a ML model and how to pick the right actions, observations, and rewards for training
• Show you how to train a model using TensorFlow and using the Unity scene; the difference between imitation learning, reinforcement learning, and other approaches; and how to train AI agents in complicated scenarios and make the real world better by leveraging the virtual
• Discuss the use of the trained model and potential applications

You’ll explore fun, engaging scenarios, including virtual self-driving cars, bipedal human-like walking robots, disembodied hands that can play tennis, and packing a warehouse efficiently using robots.

Non-game developers can learn how to use game technologies to further their understanding of machine learning fundamentals and solve problems using a combination of open source ML tools and game engines. Deep reinforcement learning using virtual environments is the beginning of an exciting new wave of AI, and game engines are on the leading edge. You’ll learn how to approach your ML work in a totally new way.

You’ll be using Unity, TensorFlow, and related tools, but all the principles and skills are general and transferrable to other game engines or simulation platforms (e.g., Open AI and the like).

It’s a bit technical, a bit creative, and you’ll leave with brand-new skills and an enthusiasm for using them. You’ll get your their own trained virtual robot (or car, or animal, or…anything you can imagine).