Evaluating Robustness of Cooperative MARL: A Model-based Approach [article]

Nhan H. Pham, Lam M. Nguyen, Jie Chen, Hoang Thanh Lam, Subhro Das, Tsui-Wei Weng
2022 arXiv   pre-print
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. Our proposed formulation can craft stronger adversarial state perturbations of c-MARL agents(s) to lower total team rewards more than existing model-free approaches. In addition, we
more » ... se the first victim-agent selection strategy which allows us to develop even stronger adversarial attack. Numerical experiments on multi-agent MuJoCo benchmarks illustrate the advantage of our approach over other baselines. The proposed model-based attack consistently outperforms other baselines in all tested environments.
arXiv:2202.03558v1 fatcat:dkvv3syfjzao3erlbvtghwgj2i