POSTED ON JULY 30, 2019 TO AI RESEARCH, ML APPLICATIONS, OPEN SOURCE
EGG: A toolkit for multi-agent language emergence simulations
By Eugène Kharitonov, Marco Baroni
What’s new:
EGG is a new toolkit that allows researchers and developers to quickly create game simulations in which two neural network agents devise their own discrete communication system in order to solve a task together. For example, in one of the implemented games, one agent sees a handwritten digit and has to invent a communication code to tell the other agent which number it represents.
A lively area of machine learning (ML) research, language emergence would benefit from a more interdisciplinary approach. However, the barrier to entry is high, as modern discrete-communication games require expertise in advanced areas of ML, such as deep sequence-to-sequence modeling and reinforcement learning. EGG lowers this barrier and  makes it possible for scientists, engineers, and hobbyists with basic programming skills to design and test new games.
Read more about EGG or watch a demonstration of EGG in action.
Why it matters: 
Human language is an extremely powerful communication system that is unique in nature. EGG helps linguists and cognitive scientists examine questions such as: Under which conditions could a discrete coding system arise? What are its properties? Which innate biases are necessary to ensure that a communication system shares the core properties of human language? 
The ability to efficiently communicate in natural language is a core aspect of what makes humans so adaptive and fast at solving problems. A rich communication code would be enormously beneficial to artificial agents. With EGG, ML experts can quickly probe the communication skills of new AI architectures.
Use it for:
EGG is useful for simulating the origins of language and studying its emergent properties. It can also be used to explore preimplemented games taken from recent studies or to design and test new agents with the ability to talk to one another.
Use this tutorial to get started with EGG.
Get it on GitHub:
EGG: Emergence of lanGuage in Games
TAGS:      OPEN SOURCE IN BRIEF
Prev
Mapping roads through deep learning and weakly supervised training
Next
Michael F. Cohen awarded 2019 Steven A. Coons award
Read More in AI ResearchView All
JUL 15, 2021
Fully Sharded Data Parallel: faster AI training with fewer GPUs
OCT 25, 2019
2019 @Scale Conference recap
OCT 17, 2019
Video @Scale 2019 recap
OCT 3, 2019
Hydra: A framework that simplifies development of complex applications
SEP 17, 2019
Register now for @Scale 2019!
SEP 5, 2019
Creating a data set and a challenge for deepfakes
Related Posts
May 21, 2019
Releasing Pythia for vision and language multimodal AI models
May 01, 2019
Open source at F8 2019
Jul 24, 2019
Mapping roads through deep learning and weakly supervised training
Related Positions
Software Engineering Manager - FRL Research
REDMOND, US
Research Manager, AI - Language Representations
MENLO PARK, US
Research Manager - Theorem Proving
PARIS, FRANCE
Research Engineer - HCI Platform Architecture | ingénieur/ingénieure d’études - Architecture de plateforme pour l’interaction personne-machine
TORONTO, CANADA
Audio Research Software Engineer
REDMOND, US
See All Jobs
Facebook © 2021
About​Careers​Privacy​Cookies​Terms​Help
To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy
Facebook EngineeringOpen SourceFacebook Open SourceAndroidiOSWebCore DataData InfrastructureDevInfraProduction EngineeringSecurityConnectivityData Center EngineeringNetworking & TrafficVideo EngineeringVirtual RealityResearch PublicationsML ApplicationsAI ResearchResearch PublicationsWatch Videos