Adversarial Attacks on Heterogeneous Multi-Agent Deep Reinforcement Learning System with Time-Delayed Data Transmission

Adversarial Attacks on Heterogeneous Multi-Agent Deep Reinforcement Learning System with Time-Delayed Data Transmission

This paper studies the gradient-based adversarial attacks on cluster-based, heterogeneous, multi-agent, deep reinforcement learning (MADRL) systems with time-delayed data transmission. The structure of the MADRL system consists of various clusters of agents. The deep Q-network (DQN) architecture pre...

Full description

Bibliographic Details
Main Authors: Neshat Elhami Fard, Rastko R. Selmic
Format: Article
Language:English
Published: MDPI AG 2022-08-01
Series:Journal of Sensor and Actuator Networks
Subjects:
multi-agent system
deep Q-network (DQN)
data transmission
gradient-based attack
defense
Online Access:https://www.mdpi.com/2224-2708/11/3/45

Internet

https://www.mdpi.com/2224-2708/11/3/45

Similar Items