Learning to Ground Multi-Agent Communication
with Autoencoders
Name
Lin-torulk-meng-eecs-2021-thesis.pdf
Description
Thesis PDF
Size
2.39 MB
Format
Adobe PDF
Checksum (MD5)
2fbf96fb90f84523f19888f1816e7f14
Author(s)
Lin, Toru
Advisor(s)
Isola, Phillip J.
Date Issued
September 2021
Publisher
Massachusetts Institute of Technology
Abstract
Communication requires having a common language, a lingua franca, between agents. This language could emerge via a consensus process between agents, but this 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.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright MIT
Persistent DSpace Link
