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 propose 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.
翻译:近年来,为多试剂合作强化学习(c-MARL)制定了大量方法,但很少探讨C-MARL剂在对抗性攻击方面的坚韧性;在本文件中,我们提议通过基于模型的方法评估c-MARL剂的坚固性;我们提议的提法可以使c-MARL剂的对抗性干扰形成更强的对抗性状态,以降低总团队的干扰,比现有的不采用模式的办法更有回报;此外,我们提议了第一个受害者-代理人选择战略,使我们能够发展更强大的对抗性攻击。关于多试剂MuJoCo基准的量化实验表明了我们的方法优于其他基线的优势。拟议的以模型为基础的攻击在所有经过测试的环境中始终优于其他基线。