Multiagent Reinforcement Learning for Integrated Network of Adaptive Traffic Signal Controllers (MARLIN-ATSC): Methodology and Large-Scale Application on Downtown Toronto

By Samah El-Tantawy, Baher Abdulhai, Hossam Abdelgawad. IEEE transactions on intelligent transportation systems (Print), 2013

499 citations recorded by the source corpus.

Subfields: Building and Construction, Control and Systems Engineering, Transportation

View Paper: https://www.semanticscholar.org/paper/7c40b442563e4629a72d9223c889366239f44eb1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Building and Construction

1. Hua Wei
2. Guanjie Zheng
3. Chacha Chen
4. Kai Xu
5. Zhenhui Jessie Li
6. Nan Xu
7. Lara Codecà
8. Jie Wang

In Control and Systems Engineering

1. Hua Wei
2. Guanjie Zheng
3. Zhenhui Jessie Li
4. Chacha Chen
5. Kai Xu
6. Nan Xu
7. Vikash V. Gayah
8. Lara Codecà

In Transportation

1. Lara Codecà
2. Jie Wang
3. Tianshu Chu
4. Zhaojian Li
5. Yuanhao Xiong
6. Hongyuan Zha
7. Hua Wei
8. Chacha Chen

Citations in the corpus

• Transfer Learning in Deep Reinforcement Learning: A Survey (2020, methodology): “It also thrives in domains such as health informatics [6], electricity networks [7], intelligent transportation systems [8], [9], to name just a few.”
• Toward A Thousand Lights: Decentralized Deep Reinforcement Learning for Large-Scale Traffic Signal Control (2020, background): “These methods can usually be scaled up easily, but they usually cannot achieve coordination since the goal of these methods ignores neighboring intersections (El-Tantawy, Abdulhai, and Abdelgawad 2013).”
• Multi-Agent Deep Reinforcement Learning for Large-Scale Traffic Signal Control (2019, methodology): “We prefer this definition over others like cumulative delay [38] and wave [14], since this reward is directly correlated to state and action, and emphasizes both traffic congestion and trip delay.”
• CoLight: Learning Network-level Cooperation for Traffic Signal Control (2019, background): “Existing studies [1, 5, 8, 9, 22] tend to select the traffic conditions from adjacent intersections and directly concatenate themwith the traffic condition of the target intersection, neglecting the fact that the traffic is changing both temporally and spatially.”
• Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2019, background): “, RSUs, to realize adaptive traffic signal controls [222].”
• Using a Deep Reinforcement Learning Agent for Traffic Signal Control (2016, background): “Previous research using reinforcement learning for traffic signal control has yielded impressive results [6][7][8],”
• Integrating Independent and Centralized Multi-agent Reinforcement Learning for Traffic Signal Network Optimization (2019, background): “On the other hand, existing work that adopt the multi-agent perspective on traffic signal optimization either fall back to independent learning [5, 12, 13] or resort to centralized optimization of coordinated agents [2, 23].”
• IntelliLight: A Reinforcement Learning Approach for Intelligent Traffic Light Control (2018, background): “Methods in [1, 2, 4, 8, 24] designed the state as discrete values like the location of vehicles or number of waited cars.”
• PressLight: Learning Max Pressure Control to Coordinate Traffic Signals in Arterial Network (2019, methodology): “Another way is to use decentralized RL agents to control the traffic signals in the multi-intersection system [4, 8, 10].”