Distributed agent-based deep reinforcement learning for large scale traffic signal control

Wu, Qiang; Wu, Jianqing; Shen, Jun; Du, Bo; Telikani, Akbar; Fahmideh, Mahdi; Liang, Chao

doi:10.1016/j.knosys.2022.108304

Cited by 49 publications

(10 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The algorithm of reinforcement learning-based traffic control is defined based on the elements of the RL systems, namely, agent, state, action, reward, and Q-matrix [36]. We present them as follows:…”

Section: Reinforcement Learningmentioning

confidence: 99%

Traffic Control Based on Integrated Kalman Filtering and Adaptive Quantized Q-Learning Framework for Internet of Vehicles

Al-Heety,

Zakaria,

Abu-Khadrah

et al. 2024

CMES

View full text Add to dashboard Cite

Intelligent traffic control requires accurate estimation of the road states and incorporation of adaptive or dynamically adjusted intelligent algorithms for making the decision. In this article, these issues are handled by proposing a novel framework for traffic control using vehicular communications and Internet of Things data. The framework integrates Kalman filtering and Q-learning. Unlike smoothing Kalman filtering, our data fusion Kalman filter incorporates a process-aware model which makes it superior in terms of the prediction error. Unlike traditional Q-learning, our Q-learning algorithm enables adaptive state quantization by changing the threshold of separating low traffic from high traffic on the road according to the maximum number of vehicles in the junction roads. For evaluation, the model has been simulated on a single intersection consisting of four roads: east, west, north, and south. A comparison of the developed adaptive quantized Q-learning (AQQL) framework with state-of-the-art and greedy approaches shows the superiority of AQQL with an improvement percentage in terms of the released number of vehicles of AQQL is 5% over the greedy approach and 340% over the state-of-the-art approach. Hence, AQQL provides an effective traffic control that can be applied in today's intelligent traffic system.

show abstract

Section: Reinforcement Learningmentioning

confidence: 99%

Traffic Control Based on Integrated Kalman Filtering and Adaptive Quantized Q-Learning Framework for Internet of Vehicles

Al-Heety,

Zakaria,

Abu-Khadrah

et al. 2024

CMES

View full text Add to dashboard Cite

show abstract

“…In addition to the above-mentioned works, recent research, such as reference [37] uses two game theory-aided RL algorithms leveraging Nash equilibrium and RL to achieve cooperation. References [38,39] explore the possibility of real-world implementation of RL-based control methods; reference [40] proposes a novel context-aware multi-agent broad reinforcement learning approach based on broad reinforcement learning for mixed pedestrian-vehicle adaptive traffic light control.…”

Section: Traffic Control Based On Rlmentioning

confidence: 99%

CenLight: Centralized traffic grid signal optimization via action and state decomposition

Ran

Lou

et al. 2023

IET Intelligent Trans Sys

View full text Add to dashboard Cite

The centralized traffic grid signal control by the reinforcement learning method is challenging due to the difficulties of searching policy in the large state and action space. In order to solve these problems, a deep reinforcement learning (DRL) method via the action and state decomposition mechanism is proposed. We apply long short-term memory to construct the agent which decomposes the high-dimensional state and action space into sub-spaces and makes decisions incrementally. This is a significant difference between our method and other methods. Through the specifically designed structure of the agent, the difficulty of searching policies can be mitigated, and our method can effectively control the traffic lights in a grid with hundreds of intersections. Experiments on synthetic data and real-world data show that our method has better performance than traditional control methods and state-of-the-art DRL-based methods with an improvement of 21% on the queue length on synthetic data and the best travel time with an improvement of 9.35% on real-world data.

show abstract

“…It has the ability of self-adaptation, self-learning, and self-coordination, and the intelligent body can achieve self-learning by interacting with the environment and can thus realize the global optimal control of complex systems. [21][22][23][24] The ultimate goal of RL is to maximize the set reward signal. RL is now widely used in several elds.…”

Section: Introductionmentioning

confidence: 99%

Reinforcement learning-based control for the thermal management of the battery and occupant compartments of electric vehicles

Zhang,

Huang,

et al. 2024

Sustainable Energy Fuels

View full text Add to dashboard Cite

show abstract

Distributed agent-based deep reinforcement learning for large scale traffic signal control

Cited by 49 publications

References 26 publications

Traffic Control Based on Integrated Kalman Filtering and Adaptive Quantized Q-Learning Framework for Internet of Vehicles

Traffic Control Based on Integrated Kalman Filtering and Adaptive Quantized Q-Learning Framework for Internet of Vehicles

CenLight: Centralized traffic grid signal optimization via action and state decomposition

Reinforcement learning-based control for the thermal management of the battery and occupant compartments of electric vehicles

Contact Info

Product

Resources

About