The Emergence of Adversarial Communication in Multi-Agent Reinforcement Learning

by   Jan Blumenkamp, et al.

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.


page 14

page 15

page 16

page 17

page 18


Modeling Sensorimotor Coordination as Multi-Agent Reinforcement Learning with Differentiable Communication

Multi-agent reinforcement learning has shown promise on a variety of coo...

A Theory of Mind Approach as Test-Time Mitigation Against Emergent Adversarial Communication

Multi-Agent Systems (MAS) is the study of multi-agent interactions in a ...

Emergent Communication through Negotiation

Multi-agent reinforcement learning offers a way to study how communicati...

FCMNet: Full Communication Memory Net for Team-Level Cooperation in Multi-Agent Systems

Decentralized cooperation in partially-observable multi-agent systems re...

MA-Dreamer: Coordination and communication through shared imagination

Multi-agent RL is rendered difficult due to the non-stationary nature of...

DistSPECTRL: Distributing Specifications in Multi-Agent Reinforcement Learning Systems

While notable progress has been made in specifying and learning objectiv...

Autonomous Agents Coordination: Action Languages meet CLP(FD) and Linda

The paper presents a knowledge representation formalism, in the form of ...

Please sign up or login with your details

Forgot password? Click here to reset