Modeling Cyber-Physical Human Systems via an Interplay Between Reinforcement Learning and Game Theory
This addresses the problem of modeling complex human-in-the-loop systems for applications like air traffic and highway management, though it appears incremental as it reviews and applies existing methods.
The paper tackles the challenge of predicting outcomes in cyber-physical systems with multiple human interactions by proposing a game theoretical approach that uses reinforcement learning to model time-extended dynamics, enabling computationally feasible modeling of multiple humans as decision makers without imposing constraints on others.
Predicting the outcomes of cyber-physical systems with multiple human interactions is a challenging problem. This article reviews a game theoretical approach to address this issue, where reinforcement learning is employed to predict the time-extended interaction dynamics. We explain that 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. We present two recent exploitations of the method to model 1) unmanned aircraft integration into the National Airspace System and 2) highway traffic. We conclude the article by providing ongoing and future work about employing, improving and validating the method. We also provide related open problems and research opportunities.