Ad Hoc Teamwork in the Presence of Adversaries
This work identifies a critical gap for deploying collaborative agents in adversarial environments, but it is incremental as it primarily suggests future research rather than presenting new results.
The paper addresses the vulnerability of ad hoc teamwork agents to adversaries in real-world applications, highlighting the lack of research in this area and proposing new directions for more robust multi-agent cyber-physical systems.
Advances in ad hoc teamwork have the potential to create agents that collaborate robustly in real-world applications. Agents deployed in the real world, however, are vulnerable to adversaries with the intent to subvert them. There has been little research in ad hoc teamwork that assumes the presence of adversaries. We explain the importance of extending ad hoc teamwork to include the presence of adversaries and clarify why this problem is difficult. We then propose some directions for new research opportunities in ad hoc teamwork that leads to more robust multi-agent cyber-physical infrastructure systems.