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.

All edits

Edits on 13 Apr, 2019
Jessica Karpinski
Jessica Karpinski edited on 13 Apr, 2019
Edits made to:
Infobox (+2 properties)
Infobox
Industry
Machine learning
Edits on 24 Feb, 2019
Daniel Frumkin
Daniel Frumkin approved a suggestion from Golden's AI on 24 Feb, 2019
Edits made to:
Article (+19/-19 characters)
Article
  • Broadcasting of agent behavior for supervised learningsupervised learning
Daniel Frumkin"Wrote article and added resources"
Daniel Frumkin edited on 24 Feb, 2019
Edits made to:
Infobox (+1 properties)
Description (+73/-28 characters)
Article (+1733/-29 characters)
People (+1 rows) (+3 cells) (+62 characters)
Further reading (+3 rows) (+12 cells) (+463 characters)
Documentaries, videos and podcasts (+1 rows) (+3 cells) (+90 characters)
Related Topics (+2 topics)
Topic thumbnail

Unity Machine Learning Agents

a collection of machine learning tools meant to help AI researchers and designers to pushquickly theand limitsefficiently ofmake theadvances technologyin game development, robotics, and more.

Article

Unity Machine Learning Agents (Unity ML-Agents), is a collection of machine learning tools meant to help AI researchers and designers to pushquickly theand limitsefficiently ofmake theadvances technologyin 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

People

Name
Role
Related Golden topics

Dr. Danny Lange

VP of AI and Machine Learning

Unity Technologies

Further reading

Title
Author
Link
Type

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

Infobox
First release
September 19, 2017
Related Topics
Daniel Frumkin"Approved suggestion from source: http://www.twitter.com/unity3d"
Daniel Frumkin approved a suggestion from Golden's AI on 24 Feb, 2019
Edits made to:
Topic thumbnail

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.

Edits on 23 Feb, 2019
Daniel Frumkin"Added description, started article."
Daniel Frumkin edited on 23 Feb, 2019
Edits made to:
Infobox (+4 properties)
Description (+118 characters)
Article (+168/-48 characters)
Documentaries, videos and podcasts (+1 rows) (+3 cells) (+106 characters)
Companies (+3 cells) (+69/-5 characters)
Categories (+1 topics)
Related Topics (+3 topics)
Topic thumbnail

Unity Machine Learning Agents

a collection of machine learning tools meant to help AI researchers and designers to push the limits of the technology

Article

Unity Machine Learning Agents (Unity ML-Agents)

Unity Machine Learning Agents (Unity ML-Agents), a collection of machine learning tools meant to help AI researchers and designers to push the limits of the technology.

Companies

Company
CEO
Location
Products/Services

UnityUnity Technologies

San Francisco

Game Development Tools

Documentaries, videos and podcasts

Title
Date
Link

Unity Obstacle Tower Challenge

February 8, 2019

Infobox
Is a
Technology
Created by
Unity Technologies
Categories
Related Topics
Daniel Frumkin"Created page"
Daniel Frumkin edited on 23 Feb, 2019
Edits made to:
Infobox (+3 properties)
Article (+48 characters)
Companies (+1 rows) (+1 cells) (+5 characters)
Article

Unity Machine Learning Agents (Unity ML-Agents)

Companies

Company
CEO
Location
Products/Services

Unity

Infobox
Daniel Frumkin"Initial topic creation"
Daniel Frumkin created this topic on 23 Feb, 2019
Edits made to:
Topic thumbnail

 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.

Golden logo
Text is available under the Creative Commons Attribution-ShareAlike 4.0; additional terms apply. By using this site, you agree to our Terms & Conditions.