Chia-Yi Hsu, Pin-Yu Chen, et al.
ICLR 2021
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 adversarial attacks has been rarely explored. In this paper, we propose to evaluate the robustness of c-MARL agents via a model-based approach, named \textbf{c-MBA}. Our proposed attack can craft much stronger adversarial state perturbations of c-MARL agents to lower total team rewards than existing model-free approaches. Our numerical experiments on two representative MARL benchmarks illustrate the advantage of our approach over other baselines: our model-based attack consistently outperforms other baselines in all tested environments.
Chia-Yi Hsu, Pin-Yu Chen, et al.
ICLR 2021
Jorge Luis Guevara Diaz, Bianca Zadrozny, et al.
NeurIPS 2022
Deepak Vijaykeerthy, Anshuman Suri, et al.
IJCNN 2019
Elvin Lo, Pin-Yu Chen
NeurIPS 2022