Learning to Ground Multi-Agent Communication with Autoencoders

Toru Lin, Minyoung Huh, Chris Stauffer, Ser-Nam Lim, Phillip Isola

Keywords: multi-agent reinforcement learning, multi-agent communication

Abstract: 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.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

TL;DR: We formulate communication grounding as a representation learning problem and propose to use observation autoencoding to learn a common grounding across all agents.

Code: https://github.com/ToruOwO/marl-ae-comm

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2110.15349/code)