Golden
Unity Machine Learning Agents

Unity Machine Learning Agents

a collection of machine learning tools meant to help AI researchers and designers to quickly and efficiently make advances in game development, robotics, and more.

Unity Machine Learning Agents (Unity ML-Agents) is a collection of machine learning tools meant to help AI researchers and designers to quickly and efficiently make advances in game development, robotics, and more.



Agents can be trained using reinforcement learning, imitation learning, neuroevolution, or other machine learning methods through a simple-to-use Python API. Unity additionally offers implementations (based on TensorFlow) of state-of-the-art algorithms to enable game developers and hobbyists to easily train intelligent agents for 2D, 3D and VR/AR games. These trained agents can be used for multiple purposes, including controlling NPC (non-player character) behavior (in a variety of settings such as multi-agent and adversarial), automated testing of game builds and evaluating different game design decisions pre-release. 

Use Cases

Unity ML-Agents can benefit:

  • Academic researchers interested in studying complex multi-agent behavior in realistic competitive and cooperative scenarios.
  • Industry researchers interested in large-scale parallel training regimes for robotics, autonomous vehicle, and other industrial applications.
  • Game developers interested in filling virtual worlds with intelligent agents each acting with dynamic and engaging behavior.

Features

The Unity ML-Agent Toolkit is an open-source solution with the following features:

  • Unity environment control from Python
  • 10+ sample Unity environments
  • Support for multiple environment configurations and training scenarios
  • Train memory-enhanced agents using deep reinforcement learning
  • Easily definable Curriculum Learning scenarios
  • Broadcasting of agent behavior for supervised learning
  • Built-in support for Imitation Learning
  • Flexible agent control with On Demand Decision Making
  • Visualizing network outputs within the environment
  • Simplified set-up with Docker
  • Wrap learning environments as a gym





Timeline

People

Name
Role
LinkedIn

Dr. Danny Lange

VP of AI and Machine Learning



Further reading

Title
Author
Link
Type
Date

Introducing: Unity Machine Learning Agents Toolkit - Unity Blog

Arthur Juliani

Web



The Obstacle Tower Challenge is live! - Unity Blog

Arthur Juliani

Web



Unity and DeepMind partner to advance AI research - Unity Blog

Danny Lange

Web



Documentaries, videos and podcasts

Title
Date
Link

Unity Machine Learning Agents

September 19, 2017

Unity Obstacle Tower Challenge

February 8, 2019

Companies

Company
CEO
Location
Products/Services

San Francisco

Game Development Tools

References