Adversarial attacks in consensus-based multi-agent reinforcement learning

Understand

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.