An Adversarial Agent-Based Design Method Using Stochastic Stackelberg Game Conditions

Abstract

Products must often endure challenging conditions while fulfilling their intended functions. Game-theoretic methods can readily create a wide variety of these conditions to consider when creating designs. This work introduces Cognitively Inspired Adversarial Agents (CIAAs) that use a Stackelberg game format to generate designs resistant to these conditions. These agents are used to generate designs while considering a multidimensional attack. Designs are produced under these adversarial conditions and compared to others generated without considering adversaries to confirm the agents’ performance. The agents create designs able to withstand multiple combined conditions.

Document Details

Document Type
Pub Defense Publication
Publication Date
Jan 29, 2021
Source ID
10.1115/1.4049862

Entities

People

  • Christopher McComb
  • Jonathan Cagan
  • Sean C. Rismiller

Organizations

  • Carnegie Mellon University
  • Defense Advanced Research Projects Agency
  • Pennsylvania State University

Tags

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Game Theory.
  • Systems Analysis and Design