# Decentralization of Multiagent Policies by Learning What to Communicate

arXiv: https://arxiv.org/abs/1901.08490 · HTML: https://mlsanity.com/paper/1901.08490/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jan 2019.

## Built on by (most cited first, 6 of 6)

- [Neurosymbolic Transformers for Multi-Agent Communication](https://mlsanity.com/paper/2101.03238/) (2021)
- [Scalable Perception-Action-Communication Loops with Convolutional and Graph Neural Networks](https://mlsanity.com/paper/2106.13358/) (2021)
- [Learning Connectivity for Data Distribution in Robot Teams](https://mlsanity.com/paper/2103.05091/) (2021)
- [Graph Neural Networks for Decentralized Multi-Agent Perimeter Defense](https://mlsanity.com/paper/2301.09689/) (2023)
- [Learning Decentralized Strategies for a Perimeter Defense Game with Graph Neural Networks](https://mlsanity.com/paper/2211.01757/) (2022)
- [A Decentralized Spike-based Learning Framework for Sequential Capture in Discrete Perimeter Defense Problem](https://mlsanity.com/paper/2305.16748/) (2023)

## Abstract (arXiv)

Effective communication is required for teams of robots to solve sophisticated collaborative tasks. In practice it is typical for both the encoding and semantics of communication to be manually defined by an expert; this is true regardless of whether the behaviors themselves are bespoke, optimization based, or learned. We present an agent architecture and training methodology using neural networks to learn task-oriented communication semantics based on the example of a communication-unaware expert policy. A perimeter defense game illustrates the system's ability to handle dynamically changing numbers of agents and its graceful degradation in performance as communication constraints are tightened or the expert's observability assumptions are broken.