Predicting the outcomes of cyber-physical systems with multiple human interactions is a challenging problem. We address this problem by exploiting a modeling framework where reinforcement learning (RL) and game theory (GT) is used together. In this framework, GT is used to model strategic decision making of humans and RL is used to model time-extended (multi-move) decisions. The most attractive feature of the method is proposing a computationally feasible approach to simultaneously model multiple humans as decision-makers, instead of determining the decision dynamics of the intelligent agent of interest and forcing the others to obey certain kinematic and dynamic constraints imposed by the environment.
Systems Laboratory 