First try on RL signal control. The base of all the methods. We provide different traffic datasets, each includes both road network (roadnet.json) and traffic flow file (flow.json), whose formats are defined in Roadnet File Format and Flow File Format respectively.

In this tutorial, we first introduce the formulation of traffic light control problems under RL, and then classify and discuss the current RL control methods from different aspects: agent formulation, policy learning approach, and coordination strategies.

This is a collection of research papers for Traffic Signal Control with RL. And the repository will be continuously updated to track the frontier of RL-based traffic signal control. Welcome to follow and star!

2023年2月4日 · 《Multi-agent Reinforcement Learning for Traffic Signal Control》 在本文中，我们将 traffic signal control (TSC) 问题制定为**折扣成本马尔可夫决策过程（MDP）**并应用多智能体强化学习（MARL）算法来获得动态TSC策略。 我们将每个交通信号交叉点建模为独立代理，代 …

This repo implements start-of-the-art mutli-agent (decentralized) deep RL algorithms for large-scale traffic signal control in SUMO-simulated environments. Available cooperation levels: Centralized: a global agent that makes global control w/ global observation, reward.

信号灯控制要解决的问题：简单来说就是什么时候哪个方向红灯，哪个方向绿灯，并且不能有冲突。 上图下面那个八个signal phase就代表八种没有冲突的组合 (这里假设了右拐不受限制，所以没有右拐)，至于为什么是这八种，这是遍历后的结果，可以看下一张图 (图来自 这论文)： 对于一个经典的四个路口的道路，只考虑存在三条车道，正反方向都有，右拐不受限制，那就只剩下8个方向，图2 (b)所示；两两组合图3 (D)所示，白色的是没有冲突，灰色的是有冲突的，同时混淆 …

2021年7月29日 · We propose a toolkit for developing and comparing reinforcement learning (RL)-based traffic signal controllers. The toolkit includes implementation of state-of-the-art deep-RL algorithms for signal control along with benchmark control problems that are based on realistic traffic scenarios.

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.

2025年1月1日 · 强化学习（Reinforcement Learning, RL）作为一种智能决策技术，近年来在交通信号控制（Traffic Signal Control, TSC）领域展现出巨大潜力。 然而，将RL模型直接应用于实际交通环境中存在诸多挑战，如模拟环境与实际交通状况的不匹配、训练过程中代理的自由探索可能 ...

2025年1月1日 · This paper addresses the challenges of deploying reinforcement learning (RL) models for traffic signal control (TSC) in real-world environments. Real-world training can prevent mismatches between simulation environments and the actual traffic conditions, thereby achieving better performance of agent upon deployment.