December 09, 2019
There is renewed interest in simulating language emergence among deep neural agents that communicate to jointly solve a task, spurred by the practical aim to develop language-enabled interactive AIs, as well as by theoretical questions about the evolution of human language. However, optimizing deep architectures connected by a discrete communication channel is technically challenging. We introduce EGG, a toolkit that simplifies the implementation of emergent-language communication games. EGG’s modular design provides a set of building blocks that the user can combine to create new games, easily navigating the optimization and architecture space. We hope that the tool will lower the technical barrier, and encourage researchers from various backgrounds to work in this exciting area.
Publisher
NeurIPS
Research Topics
October 02, 2026
Aykut Arslan
October 02, 2026
October 02, 2026
Andres Barei Bueno
October 02, 2026
October 02, 2026
Anindya Dey, Gabriel Herczeg, An Huang, Nicolas Jaramillo Torres, Jacob H. Swenberg
October 02, 2026
October 02, 2026
Joseph Phillip Brennan, Milana Golich
October 02, 2026
