Learning to Calibrate Hybrid Hyperparameters: A Study on Traffic Simulation
Document Type
Conference Proceeding
Publication Date
6-21-2023
Abstract
Traffic simulation is an important computational technique that models the behavior and interactions of vehicles, pedestrians, and infrastructure in a transportation system. Calibration, which involves adjusting simulation parameters to match real-world data, is a key challenge in traffic simulation. Traffic simulators involve multiple models with hybrid hyperparameters, which could be either categorical or continuous. In this paper, we present CHy2, an approach that generates a set of hyperparameters for simulator calibration using generative adversarial imitation learning. CHy2 learns to mimic expert behavior models by rewarding hyperparameters that deceive a discriminator trained to classify policy-generated and expert trajectories. Specifically, we propose a hybrid architecture of actor-critic algorithms to handle the hybrid choices between hyperparameters. Experimental results show that CHy2 outperforms previous methods in calibrating traffic simulators.
Identifier
85163824347 (Scopus)
ISBN
[9798400700309]
Publication Title
ACM International Conference Proceeding Series
External Full Text Location
https://doi.org/10.1145/3573900.3591113
First Page
144
Last Page
147
Grant
2153311
Fund Ref
National Science Foundation
Recommended Citation
Xu, Wanpeng and Wei, Hua, "Learning to Calibrate Hybrid Hyperparameters: A Study on Traffic Simulation" (2023). Faculty Publications. 1652.
https://digitalcommons.njit.edu/fac_pubs/1652
