Cite
@InProceedings{10.1007/978-3-032-08067-7_3,
author=”Xie, Qintong
and Koh, Edward
and Cadet, Xavier
and Chin, Peter”,
editor=”Baras, John S.
and Papavassiliou, Symeon
and Tsiropoulou, Eirini Eleni
and Sayin, Muhammed O.”,
title=”Nash Q-Network for Multi-agent Cybersecurity Simulation”,
booktitle=”Game Theory and AI for Security”,
year=”2026″,
publisher=”Springer Nature Switzerland”,
address=”Cham”,
pages=”43–60″,
abstract=”Cybersecurity defense involves interactions between adversarial parties (namely defenders and hackers), making multi-agent reinforcement learning (MARL) an ideal approach for modeling and learning strategies for these scenarios. This paper addresses the challenge of simultaneous multi-agent training in complex environments and introduces a Nash Q-Network that enables learning in a partial observation environment. Facilitates learning in partially observed settings. We demonstrate the successful implementation of this algorithm in a notable complex cyber defense simulation treated as a two-player zero-sum Markov game setting. We propose the Nash Q-Network, which aims to learn Nash-optimal strategies that translate to robust defenses in cybersecurity settings. Our approach incorporates aspects of proximal policy optimization (PPO), deep Q-network (DQN), and the Nash-Q algorithm, addressing common challenges like non-stationarity and instability in multi-agent learning. The training process employs distributed data collection and carefully designed neural architectures for both agents and critics.”,
isbn=”978-3-032-08067-7″
}