Generation of Games for Opponent Model Differentiation
This work addresses the challenge of identifying strategic differences between opponent models for multiagent systems, though it is incremental as it builds on prior psychological data and game optimization methods.
The paper tackled the problem of differentiating opponent models in adversarial settings by linking model parameters to psychological traits and optimizing over parametrized games, resulting in the creation of games where model differences are profound.
Protecting against adversarial attacks is a common multiagent problem. Attackers in the real world are predominantly human actors, and the protection methods often incorporate opponent models to improve the performance when facing humans. Previous results show that modeling human behavior can significantly improve the performance of the algorithms. However, modeling humans correctly is a complex problem, and the models are often simplified and assume humans make mistakes according to some distribution or train parameters for the whole population from which they sample. In this work, we use data gathered by psychologists who identified personality types that increase the likelihood of performing malicious acts. However, in the previous work, the tests on a handmade game could not show strategic differences between the models. We created a novel model that links its parameters to psychological traits. We optimized over parametrized games and created games in which the differences are profound. Our work can help with automatic game generation when we need a game in which some models will behave differently and to identify situations in which the models do not align.