Deep Reinforcement Learning for Traffic Light Control in Vehicular Networks

@article{Liang2018DeepRL,
  title={Deep Reinforcement Learning for Traffic Light Control in Vehicular Networks},
  author={Xiaoyuan Liang and Xunsheng Du and Guiling Wang and Zhu Han},
  journal={ArXiv},
  year={2018},
  volume={abs/1803.11115}
}
Existing inefficient traffic light control causes numerous problems, such as long delay and waste of energy. To improve efficiency, taking real-time traffic information as an input and dynamically adjusting the traffic light duration accordingly is a must. In terms of how to dynamically adjust traffic signals’ duration, existing works either split the traffic signal into equal duration or extract limited traffic information from the real data. In this paper, we study how to decide the traffic… 
View PDF on arXiv
View With Semantic Reader
111 Citations
Highly Influential Citations
8
Background Citations
43
Methods Citations
25
Results Citations
2

111 Citations

Citation Type

Citation Type

Deep Reinforcement Learning for Traffic Signal Control: A Review
TLDR
This article presents a review of the attributes of traffic signal control (TSC), as well as DRL architectures and methods applied to TSC, which helps to understand how DRL has been applied to address traffic congestion and achieve performance enhancement.
A Reinforcement Learning Approach for Intelligent Traffic Signal Control at Urban Intersections
TLDR
This paper uses neural networks as Q-function approximator (a.k.a. Q-network) to deal with the complex traffic signal control problem where the state space could be huge and the action space can be discrete, and proposes a RL approach for traffic sign control at urban intersections.
AttendLight: Universal Attention-Based Reinforcement Learning Model for Traffic Signal Control
TLDR
AttendLight outperforms both classical and other RL-based approaches on all cases in both regimes, and the model works for any intersection configuration, as long as a similar configuration is represented in the training set.
Fairness Control of Traffic Light via Deep Reinforcement Learning
TLDR
This paper studies the fairness control of traffic light and proposes a deep reinforcement learning algorithm to optimize the fairness of all drivers’ waiting time and wishes to shed light on complementing the entire framework of reinforcement learning with research on fairness control.
Improving Traffic Safety and Efficiency by Adaptive Signal Control Systems Based on Deep Reinforcement Learning
Towards Robust Deep Reinforcement Learning for Traffic Signal Control: Demand Surges, Incidents and Sensor Failures
TLDR
This paper develops an open-source callback-based framework for promoting the flexible evaluation of different deep RL configurations under a traffic simulation environment and investigates how deep RL-based adaptive traffic controllers perform under different scenarios.
Traffic Signal Control Using Deep Reinforcement Learning with Multiple Resources of Rewards
TLDR
A DRL-based framework that uses multiple rewards for multiple objectives to solve the difficulty of assessing behaviours by single numeric reward and control traffic flows more steadily is proposed.
Heterogeneous Multi-Agent Deep Reinforcement Learning for Traffic Lights Control
TLDR
Independent Deep Q-Network is proposed to train multiple heterogeneous agents in heterogeneous UTC with the best performance achieved by the combination of IDQN with prioritized experience replay but without fingerprinting.
A physics-informed reinforcement learning-based strategy for local and coordinated ramp metering
Area-wide traffic signal control based on a deep graph Q-Network (DGQN) trained in an asynchronous manner
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 28 REFERENCES
Video Demo: Deep Reinforcement Learning for Coordination in Traffic Light Control
This video demonstration contrasts two approaches to coordination in traffic light control using reinforcement learning: earlier work, based on a deconstruction of the state space into a linear…
Deep Reinforcement Learning with Double Q-Learning
TLDR
This paper proposes a specific adaptation to the DQN algorithm and shows that the resulting algorithm not only reduces the observed overestimations, as hypothesized, but that this also leads to much better performance on several games.
Using a Deep Reinforcement Learning Agent for Traffic Signal Control
TLDR
This work applies modern deep reinforcement learning methods to build a truly adaptive traffic signal control agent in the traffic microsimulator SUMO, using a new state space, the discrete traffic state encoding, which is information dense.
Recent Development and Applications of SUMO - Simulation of Urban MObility
TLDR
The current state of the SUMO package, its major applications, both by research topic and by example, as well as future developments and extensions are described.
Dueling Network Architectures for Deep Reinforcement Learning
TLDR
This paper presents a new neural network architecture for model-free reinforcement learning that leads to better policy evaluation in the presence of many similar-valued actions and enables the RL agent to outperform the state-of-the-art on the Atari 2600 domain.
Traffic signal timing via deep reinforcement learning
TLDR
A set of algorithms to design signal timing plans via deep reinforcement learning to set up a deep neural network to learn the Q-function of reinforcement learning from the sampled traffic state/control inputs and the corresponding traffic system performance output.
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
TLDR
This work proposes a Parametric Rectified Linear Unit (PReLU) that generalizes the traditional rectified unit and derives a robust initialization method that particularly considers the rectifier nonlinearities.
A tutorial survey on vehicular ad hoc networks
TLDR
An overview of the field of vehicular ad hoc networks is given, providing motivations, challenges, and a snapshot of proposed solutions.
A Convolutional Neural Network for Transportation Mode Detection Based on Smartphone Platform
  • Xiaoyuan Liang, Guiling Wang
  • Computer Science
    2017 IEEE 14th International Conference on Mobile Ad Hoc and Sensor Systems (MASS)
  • 2017
TLDR
A light-weight and energy-efficient transportation mode detection application only using the accelerometer sensor on smartphones and build a convolutional neural network to determine transportation modes.
Q-Learning Based Traffic Optimization in Management of Signal Timing Plan
TLDR
A good valuable performance has been shown by the proposed learning algorithm that able to improve the traffic signal timing plan for the dynamic traffic flows within a traffic network.
...
1
2
3
...