Learning to Ground Multi-Agent Communication with Autoencoders

10/28/2021
by   Toru Lin, et al.
0

Communication requires having a common language, a lingua franca, between agents. This language could emerge via a consensus process, but it may require many generations of trial and error. Alternatively, the lingua franca can be given by the environment, where agents ground their language in representations of the observed world. We demonstrate a simple way to ground language in learned representations, which facilitates decentralized multi-agent communication and coordination. We find that a standard representation learning algorithm – autoencoding – is sufficient for arriving at a grounded common language. When agents broadcast these representations, they learn to understand and respond to each other's utterances and achieve surprisingly strong task performance across a variety of multi-agent communication environments.

READ FULL TEXT

page 5

page 9

research
03/07/2022

Learning to Ground Decentralized Multi-Agent Communication with Contrastive Learning

For communication to happen successfully, a common language is required ...
research
06/05/2022

Efficient decentralized multi-agent learning in asymmetric queuing systems

We study decentralized multi-agent learning in bipartite queuing systems...
research
09/20/2021

Learning to Improve Representations by Communicating About Perspectives

Effective latent representations need to capture abstract features of th...
research
04/20/2020

A Practical Guide to Studying Emergent Communication through Grounded Language Games

The question of how an effective and efficient communication system can ...
research
09/18/2023

Ontology-Based Feedback to Improve Runtime Control for Multi-Agent Manufacturing Systems

Improving the overall equipment effectiveness (OEE) of machines on the s...
research
11/04/2021

Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel

While multi-agent reinforcement learning has been used as an effective m...
research
12/30/2019

Improved Structural Discovery and Representation Learning of Multi-Agent Data

Central to all machine learning algorithms is data representation. For m...

Please sign up or login with your details

Forgot password? Click here to reset