Ad Hoc Teamwork in the Presence of Adversaries

TL;DR

This paper emphasizes the importance of developing ad hoc teamwork agents resilient to adversaries, highlighting the challenges and proposing new research directions for robust multi-agent cyber-physical systems.

Contribution

It identifies the gap in ad hoc teamwork research regarding adversaries and suggests future research directions to enhance robustness in real-world multi-agent systems.

Findings

Highlights the vulnerability of ad hoc teamwork agents to adversaries

Clarifies the challenges in extending ad hoc teamwork to adversarial settings

Proposes new research opportunities for robust multi-agent systems

Abstract

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.