Enhancing the Robustness of QMIX against State-adversarial Attacks

no code implementations • 3 Jul 2023 • Weiran Guo, Guanjun Liu, Ziyuan Zhou, Ling Wang, Jiacun Wang

To increase the robustness of multi-agent reinforcement learning (MARL) algorithms, we train models using a variety of attacks in this research.

Multi-agent Reinforcement Learning reinforcement-learning

Robustness Testing for Multi-Agent Reinforcement Learning: State Perturbations on Critical Agents

no code implementations • 9 Jun 2023 • Ziyuan Zhou, Guanjun Liu

Then, adversarial state perturbations of the critical agents are generated based on the worst-case joint actions.

Multi-agent Reinforcement Learning reinforcement-learning

Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges

no code implementations • 17 May 2023 • Ziyuan Zhou, Guanjun Liu, Ying Tang

This paper aims to review methods and applications and point out research trends and visionary prospects for the next decade.

Multi-agent Reinforcement Learning reinforcement-learning

Partially Observable Mean Field Multi-Agent Reinforcement Learning Based on Graph-Attention

no code implementations • 25 Apr 2023 • Min Yang, Guanjun Liu, Ziyuan Zhou

In this paper, we propose a novel multi-agent reinforcement learning algorithm, Partially Observable Mean Field Multi-Agent Reinforcement Learning based on Graph--Attention (GAMFQ) to remedy this flaw.

Graph Attention Multi-agent Reinforcement Learning +1

RoMFAC: A robust mean-field actor-critic reinforcement learning against adversarial perturbations on states

no code implementations • 15 May 2022 • Ziyuan Zhou, Guanjun Liu

Multi-agent deep reinforcement learning makes optimal decisions dependent on system states observed by agents, but any uncertainty on the observations may mislead agents to take wrong actions.

reinforcement-learning Reinforcement Learning (RL)