# Towards True Lossless Sparse Communication in Multi-Agent Systems

arXiv: https://arxiv.org/abs/2212.00115 · HTML: https://mlsanity.com/paper/2212.00115/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 30 Nov 2022.

## Builds on (most cited first, 22 of 22)

- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [TarMAC: Targeted Multi-Agent Communication](https://mlsanity.com/paper/1810.11187/) (2018)
- [Multi-Agent Cooperation and the Emergence of (Natural) Language](https://mlsanity.com/paper/1612.07182/) (2016)
- [Learning Attentional Communication for Multi-Agent Cooperation](https://mlsanity.com/paper/1805.07733/) (2018)
- [Emergent Multi-Agent Communication in the Deep Learning Era](https://mlsanity.com/paper/2006.02419/) (2020)
- [Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks](https://mlsanity.com/paper/1812.09755/) (2018)
- [Learning Efficient Multi-agent Communication: An Information Bottleneck Approach](https://mlsanity.com/paper/1911.06992/) (2019)
- [Learning Individually Inferred Communication for Multi-Agent Cooperation](https://mlsanity.com/paper/2006.06455/) (2020)
- [Biases for Emergent Communication in Multi-agent Reinforcement Learning](https://mlsanity.com/paper/1912.05676/) (2019)
- [Learning Transferable Cooperative Behavior in Multi-Agent Teams](https://mlsanity.com/paper/1906.01202/) (2019)
- [Learning to Ground Multi-Agent Communication with Autoencoders](https://mlsanity.com/paper/2110.15349/) (2021)
- [Learning Agent Communication under Limited Bandwidth by Message Pruning](https://mlsanity.com/paper/1912.05304/) (2019)
- [Emergent Discrete Communication in Semantic Spaces](https://mlsanity.com/paper/2108.01828/) (2021)
- [Learning Emergent Discrete Message Communication for Cooperative Reinforcement Learning](https://mlsanity.com/paper/2102.12550/) (2021)
- [Event-Triggered Multi-agent Reinforcement Learning with Communication under Limited-bandwidth Constraint](https://mlsanity.com/paper/2010.04978/) (2020)
- [Towards Human-Agent Communication via the Information Bottleneck Principle](https://mlsanity.com/paper/2207.00088/) (2022)
- [Interpretable Learned Emergent Communication for Human-Agent Teams](https://mlsanity.com/paper/2201.07452/) (2022)
- [Minimizing Communication while Maximizing Performance in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2106.08482/) (2021)
- [Noncooperative Herding With Control Barrier Functions: Theory and Experiments](https://mlsanity.com/paper/2204.10945/) (2022)

## Built on by (most cited first, 4 of 4)

- [Prime Agent: A Self-Improving RLM Harness](https://mlsanity.com/paper/2608.23552/) (2026)
- [On the Role of Emergent Communication for Social Learning in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2302.14276/) (2023)
- [Learning Communication Between Heterogeneous Agents in Multi-Agent Reinforcement Learning for Autonomous Cyber Defence](https://mlsanity.com/paper/2603.20279/) (2026)
- [MUTE: Return-Preserving Communication Unlearning for Efficient Multi-Agent Coordination](https://mlsanity.com/paper/2607.03473/) (2026)

## Abstract (arXiv)

Communication enables agents to cooperate to achieve their goals. Learning when to communicate, i.e., sparse (in time) communication, and whom to message is particularly important when bandwidth is limited. Recent work in learning sparse individualized communication, however, suffers from high variance during training, where decreasing communication comes at the cost of decreased reward, particularly in cooperative tasks. We use the information bottleneck to reframe sparsity as a representation learning problem, which we show naturally enables lossless sparse communication at lower budgets than prior art. In this paper, we propose a method for true lossless sparsity in communication via Information Maximizing Gated Sparse Multi-Agent Communication (IMGS-MAC). Our model uses two individualized regularization objectives, an information maximization autoencoder and sparse communication loss, to create informative and sparse communication. We evaluate the learned communication `language' through direct causal analysis of messages in non-sparse runs to determine the range of lossless sparse budgets, which allow zero-shot sparsity, and the range of sparse budgets that will inquire a reward loss, which is minimized by our learned gating function with few-shot sparsity. To demonstrate the efficacy of our results, we experiment in cooperative multi-agent tasks where communication is essential for success. We evaluate our model with both continuous and discrete messages. We focus our analysis on a variety of ablations to show the effect of message representations, including their properties, and lossless performance of our model.