# The Emergence of Adversarial Communication in Multi-Agent Reinforcement Learning

arXiv: https://arxiv.org/abs/2008.02616 · HTML: https://mlsanity.com/paper/2008.02616/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2020.

## Built on by (most cited first, 28 of 28)

- [Heterogeneous Multi-Robot Reinforcement Learning](https://mlsanity.com/paper/2301.07137/) (2023)
- [Scalable Multi-Agent Model-Based Reinforcement Learning](https://mlsanity.com/paper/2205.15023/) (2022)
- [Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learning](https://mlsanity.com/paper/2108.03803/) (2021)
- [Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence](https://mlsanity.com/paper/2302.03322/) (2023)
- [A Review of the Applications of Deep Learning-Based Emergent Communication](https://mlsanity.com/paper/2407.03302/) (2024)
- [Distributed Reinforcement Learning for Robot Teams: A Review](https://mlsanity.com/paper/2204.03516/) (2022)
- [Graph Neural Networks for Decentralized Multi-Robot Submodular Action Selection](https://mlsanity.com/paper/2105.08601/) (2021)
- [System Neural Diversity: Measuring Behavioral Heterogeneity in Multi-Agent Learning](https://mlsanity.com/paper/2305.02128/) (2023)
- [Beyond Robustness: A Taxonomy of Approaches towards Resilient Multi-Robot Systems](https://mlsanity.com/paper/2109.12343/) (2021)
- [A Framework for Real-World Multi-Robot Systems Running Decentralized GNN-Based Policies](https://mlsanity.com/paper/2111.01777/) (2021)
- [Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems](https://mlsanity.com/paper/2206.10158/) (2022)
- [Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL](https://mlsanity.com/paper/2305.17342/) (2023)
- [Cooperative AI via Decentralized Commitment Devices](https://mlsanity.com/paper/2311.07815/) (2023)
- [Trust-based Consensus in Multi-Agent Reinforcement Learning Systems](https://mlsanity.com/paper/2205.12880/) (2022)
- [Mediated Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2306.08419/) (2023)
- [Graph learning in robotics: a survey](https://mlsanity.com/paper/2310.04294/) (2023)
- [CoDreamer: Communication-Based Decentralised World Models](https://mlsanity.com/paper/2406.13600/) (2024)
- [The Holy Grail of Multi-Robot Planning: Learning to Generate Online-Scalable Solutions from Offline-Optimal Experts](https://mlsanity.com/paper/2107.12254/) (2021)
- [SoK: Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2301.04299/) (2023)
- [Robust Multi-agent Communication via Multi-view Message Certification](https://mlsanity.com/paper/2305.13936/) (2023)
- [On the Trade-Off between Stability and Representational Capacity in Graph Neural Networks](https://mlsanity.com/paper/2312.02372/) (2023)
- [Stimulate the Potential of Robots via Competition](https://mlsanity.com/paper/2403.10487/) (2024)
- [Multi-Agent Conditional Diffusion Model with Mean Field Communication as Wireless Resource Allocation Planner](https://mlsanity.com/paper/2510.22969/) (2025)
- [See What the Robot Can't See: Learning Cooperative Perception for Visual Navigation](https://mlsanity.com/paper/2208.00759/) (2022)
- [A Cooperative Reinforcement Learning Environment for Detecting and Penalizing Betrayal](https://mlsanity.com/paper/2210.12841/) (2022)
- [Generalizability of Graph Neural Networks for Decentralized Unlabeled Motion Planning](https://mlsanity.com/paper/2409.19829/) (2024)
- [Collaborative State Fusion in Partially Known Multi-agent Environments](https://mlsanity.com/paper/2410.15137/) (2024)
- [Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2605.05020/) (2026)

## Abstract (arXiv)

Many real-world problems require the coordination of multiple autonomous agents. Recent work has shown the promise of Graph Neural Networks (GNNs) to learn explicit communication strategies that enable complex multi-agent coordination. These works use models of cooperative multi-agent systems whereby agents strive to achieve a shared global goal. When considering agents with self-interested local objectives, the standard design choice is to model these as separate learning systems (albeit sharing the same environment). Such a design choice, however, precludes the existence of a single, differentiable communication channel, and consequently prohibits the learning of inter-agent communication strategies. In this work, we address this gap by presenting a learning model that accommodates individual non-shared rewards and a differentiable communication channel that is common among all agents. We focus on the case where agents have self-interested objectives, and develop a learning algorithm that elicits the emergence of adversarial communications. We perform experiments on multi-agent coverage and path planning problems, and employ a post-hoc interpretability technique to visualize the messages that agents communicate to each other. We show how a single self-interested agent is capable of learning highly manipulative communication strategies that allows it to significantly outperform a cooperative team of agents.