PROTECT -- A Deployed Game Theoretic System for Strategic Security Allocation for the United States Coast Guard

An, Bo (University of Southern California) | Shieh, Eric (University of Southern California) | Tambe, Milind (University of Southern California) | Yang, Rong (University of Southern California) | Baldwin, Craig (United States Coast Guard) | DiRenzo, Joseph (United States Coast Guard) | Maule, Ben (United States Coast Guard) | Meyer, Garrett (United States Coast Guard)

AI Magazine 

While three deployed applications of game theory for security have recently been reported, we as a community of agents and AI researchers remain in the early stages of these deployments; there is a continuing need to understand the core principles for innovative security applications of game theory. PROTECT is premised on an attacker-defender Stackelberg game model and offers five key innovations. First, this system is a departure from the assumption of perfect adversary rationality noted in previous work, relying instead on a quantal response (QR) model of the adversary's behavior --- to the best of our knowledge, this is the first real-world deployment of the QR model. Fourth, our experimental results illustrate that PROTECT's QR model more robustly handles real-world uncertainties than a perfect rationality model.