Adversarial attacks in consensus-based multi-agent reinforcement learning

Authors: Martin Figura, Krishna Chaitanya Kosaraju, Vijay Gupta
Published: 2021-03-11

Source: https://arxiv.org/abs/2103.06967

PDF: https://arxiv.org/pdf/2103.06967

Labels Predicted by AI

マルチエージェント強化学習 収束分析 敵対的攻撃手法

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

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.