In recent years, a proliferation of methods were developed for cooperative multi-agent reinforcement learning (c-MARL). However, the robustness of c-MARL agents against …
In recent years, a proliferation of methods were developed for cooperative multi-agent reinforcement learning (c-MARL). However, the robustness of c-MARL agents against …
Y Hu, Z Zhang - arXiv preprint arXiv:2205.09362, 2022 - arxiv.org
Cooperative multi-agent reinforcement learning (cMARL) has many real applications, but the policy trained by existing cMARL algorithms is not robust enough when deployed. There …
J Guo, Y Chen, Y Hao, Z Yin… - Proceedings of the …, 2022 - openaccess.thecvf.com
While deep neural networks (DNNs) have strengthened the performance of cooperative multi-agent reinforcement learning (c-MARL), the agent policy can be easily perturbed by …
Z Chen, Y Liao, Y Zhao, Z Dai, J Zhao - arXiv preprint arXiv:2406.17425, 2024 - arxiv.org
Cooperative Multi-Agent Reinforcement Learning (CMARL) strategies are well known to be vulnerable to adversarial perturbations. Previous works on adversarial attacks have …
M Standen, J Kim, C Szabo - arXiv preprint arXiv:2301.04299, 2023 - arxiv.org
Multi-Agent Reinforcement Learning (MARL) is vulnerable to Adversarial Machine Learning (AML) attacks and needs adequate defences before it can be used in real world …
L Zan, X Zhu, ZL Hu - Complex & Intelligent Systems, 2023 - Springer
Existing research shows that cooperative multi-agent deep reinforcement learning (c- MADRL) is vulnerable to adversarial attacks, and c-MADRL is increasingly being applied to …
Z Zhou, G Liu - arXiv preprint arXiv:2306.06136, 2023 - arxiv.org
Multi-Agent Reinforcement Learning (MARL) has been widely applied in many fields such as smart traffic and unmanned aerial vehicles. However, most MARL algorithms are …
The robustness of deep cooperative multi-agent reinforcement learning (MARL) is of great concern and limits the application to real-world risk-sensitive tasks. Adversarial attack is a …