M Shearer and MP Wellman
10th International Workshop on Agents in Traffic and Transportation, July 2018.
We develop an incentive scheme for a hub-to-shuttle campus transit system, encouraging riders to shift travel times to improve system efficiency. Riders are modeled as agents with loss functions in order to evaluate social welfare in the incentive scheme. Incentives are calculated based on a predictive wait-time model trained via Gaussian process regression. Experiments show that the system’s total loss decreases, but the average wait time increases. This leads to the conclusion that there is room for improvement in the predictive wait time model.