Adversarial attacks in consensus-based multi-agent reinforcement learning

Recently, many cooperative distributed multi-agent reinforcement learning (MARL) algorithms have been proposed in the literature. In this work, we study the effect of adversarial attacks on a network that employs a consensus-based MARL algorithm. We show that an adversarial agent can persuade all th...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Figura, Martin, Krishna Chaitanya Kosaraju, Gupta, Vijay
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 11.03.2021
Subjects
Algorithms
Machine learning
Multiagent systems
Online AccessGet full text

Cover

More Information
Summary:Recently, many cooperative distributed multi-agent reinforcement learning (MARL) algorithms have been proposed in the literature. In this work, we study the effect of adversarial attacks on a network that employs a consensus-based MARL algorithm. We show that an adversarial agent can persuade all the other agents in the network to implement policies that optimize an objective that it desires. In this sense, the standard consensus-based MARL algorithms are fragile to attacks.
ISSN:2331-8422