HumanLight: Incentivizing Ridesharing via Human-centric Deep Reinforcement Learning in Traffic Signal Control

1 code implementation • 5 Apr 2023 • Dimitris M. Vlachogiannis, Hua Wei, Scott Moura, Jane Macfarlane

Apart from adopting FRAP, a state-of-the-art (SOTA) base model, HumanLight introduces the concept of active vehicles, loosely defined as vehicles in proximity to the intersection within the action interval window.