AI agents need to be robust to unexpected changes in their environment in order to safely operate in real-world scenarios. While some work has been done on this type of robustness in the single-agent case, in this work we introduce the idea that collaboration with other agents can help agents adapt to environment perturbations in multi-agent reinforcement learning settings. We first formalize this notion of resilience of a group of agents. We then empirically evaluate different collaboration protocols and examine their effect on resilience. We see that all of the collaboration approaches considered lead to greater resilience compared to baseline, in line with our hypothesis. We discuss future direction and the general relevance of the concept of resilience introduced in this work.
翻译:AI代理机构需要强力应对其环境的意外变化,以便在现实世界中安全运作。虽然在单一试剂案例中已经就这种类型的稳健性做了一些工作,但在这项工作中,我们提出这样的想法,即与其他代理机构的合作可以帮助代理机构适应多剂强化学习环境中的环境扰动。我们首先正式确定关于一组代理机构的抗御力的概念。然后,我们根据经验评估不同的合作协议,并研究其对抗御能力的影响。我们发现,所有考虑的合作方针都导致与基线相比,根据我们的假设提高抗御力。我们讨论了未来的方向和在这项工作中引入的抗御力概念的一般相关性。