Timezone: »

 
Poster
Learning to Ground Multi-Agent Communication with Autoencoders
Toru Lin · Jacob Huh · Christopher Stauffer · Ser Nam Lim · Phillip Isola

Fri Dec 10 08:30 AM -- 10:00 AM (PST) @
in Poster Session 8 »

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.

Keywords: Reinforcement Learning and Planning · Representation Learning

Author Information

Toru Lin (MIT)
Jacob Huh (MIT)
Christopher Stauffer (Facebook)
Ser Nam Lim (Facebook AI)
Phillip Isola (Massachusetts Institute of Technology)

More from the Same Authors