Welcome to

LibSignal

An Open Environment For
Traffic Signal Control.

Scroll Down

About LibSignal

LibSignal is 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.

App Screenshots

Features

Cross simulator

LibSignal provides transformations across different simulators, including SUMO, CityFlow and CBEngine, enabling comparisons between different algorithms originally conducted in different simulators.

Unified Interface

LibSignal provides unified interfaces to process and retrieve common information from different simulators for state, reward and evaluation metrics.

Comprehensive Models

LibSignal implements three baseline controllers and seven RL-based controllers to form a comprehensive model warehouse. Meanwhile, LibSignal collects 9 commonly used datasets.

Easy To Customize

LibSignal enables a modular design of different components, allowing users to flexibly insert customized components into the library.

Up-to-date Literature

LigSignal maintains RL-based traffic signal control papers published in the recent years on top conferences and journals and their workshop papers. We will continue to update the collection.

Extensible

LibSignal has an OpenAI Gym interface which allows easy deployment of standard RL algorithms and supports existing RL frameworks and different simulators.

Get Started Now!

Run in Google Colab,
or download the environment and compile the source code.