Driver modeling through deep reinforcement learning and behavioral game theory

Abstract

In this work, a synergistic combination of deep reinforcement learning and hierarchical game theory is proposed as a modeling framework for behavioral predictions of drivers in highway driving scenarios. The modeling framework presented in this work can be used in a high-fidelity traffic simulator consisting of multiple human decision-makers. This simulator can reduce the time and effort spent for testing autonomous vehicles by allowing safe and quick assessment of self-driving control algorithms. To demonstrate the fidelity of the proposed modeling framework, game-theoretical driver models are compared with real human driver behavior patterns extracted from two different sets of traffic data.