LibSignal: An Open Library for Traffic Signal Control
This library addresses the need for standardized evaluation in traffic signal control research, facilitating reproducible and fair comparisons across different simulators and datasets, though it is incremental as it builds on existing methods.
The paper introduces LibSignal, an open library for cross-simulator comparison of reinforcement learning models in traffic signal control, implementing state-of-the-art models with unified metrics and validating them across simulators like SUMO and CityFlow to enable fair performance comparisons.
This paper introduces a library for cross-simulator comparison of reinforcement learning models in traffic signal control tasks. This library is developed to implement recent state-of-the-art reinforcement learning models with extensible interfaces and unified cross-simulator evaluation metrics. It supports commonly-used simulators in traffic signal control tasks, including Simulation of Urban MObility(SUMO) and CityFlow, and multiple benchmark datasets for fair comparisons. We conducted experiments to validate our implementation of the models and to calibrate the simulators so that the experiments from one simulator could be referential to the other. Based on the validated models and calibrated environments, this paper compares and reports the performance of current state-of-the-art RL algorithms across different datasets and simulators. This is the first time that these methods have been compared fairly under the same datasets with different simulators.