Traffic Light Control Using Deep Policy-Gradient and Value-Function Based Reinforcement Learning

2017-04-28 · Seyed Sajad Mousavi, Michael Schukat, Enda Howley

Recent advances in combining deep neural network architectures with reinforcement learning techniques have shown promising potential results in solving complex control problems with high dimensional state and action spaces. Inspired by these successes, in this paper, we build two kinds of reinforcement learning algorithms: deep policy-gradient and value-function based agents which can predict the best possible traffic signal for a traffic intersection. At each time step, these adaptive traffic light control agents receive a snapshot of the current state of a graphical traffic simulator and produce control signals. The policy-gradient based agent maps its observation directly to the control signal, however the value-function based agent first estimates values for all legal control signals. The agent then selects the optimal control action with the highest value. Our methods show promising results in a traffic network simulated in the SUMO traffic simulator, without suffering from instability issues during the training process.

📄 PDF Abstract BibTeX arXiv:1704.08883

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Adaptive Traffic Light Control for Competing Vehicle and Pedestrian Flows

2023-03-14 · Yingqing Chen, Christos G. Cassandras

We study the Traffic Light Control (TLC) problem for a single intersection, considering both straight driving vehicle flows and corresponding crossing pedestrian flows with the goal of achieving a fair jointly optimal sh…

Intelligent Traffic Light via Policy-based Deep Reinforcement Learning

2021-12-27 · Yue Zhu, Mingyu Cai, Chris Schwarz, Junchao Li 외

Intelligent traffic lights in smart cities can optimally reduce traffic congestion. In this study, we employ reinforcement learning to train the control agent of a traffic light on a simulator of urban mobility. As a dif…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Deep Deterministic Policy Gradient for Urban Traffic Light Control

2017-03-27 · Noe Casas

Traffic light timing optimization is still an active line of research despite the wealth of scientific literature on the topic, and the problem remains unsolved for any non-toy scenario. One of the key issues with traffi…

Integrated Decision and Control at Multi-Lane Intersections with Mixed Traffic Flow

2021-08-30 · Jianhua Jiang, Yangang Ren, Yang Guan, Shengbo Eben Li 외

Autonomous driving at intersections is one of the most complicated and accident-prone traffic scenarios, especially with mixed traffic participants such as vehicles, bicycles and pedestrians. The driving policy should ma…

Autonomous Driving Model Predictive Control Reinforcement Learning (RL)

Deep Reinforcement Learning for Traffic Light Control in Intelligent Transportation Systems

2023-02-04 · Ming Zhu, Xiao-Yang Liu, Sem Borst, Anwar Walid

Smart traffic lights in intelligent transportation systems (ITSs) are envisioned to greatly increase traffic efficiency and reduce congestion. Deep reinforcement learning (DRL) is a promising approach to adaptively contr…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)Traffic Signal Control