citations.txt

REFERENCES
[1] Baher Abdulhai, Rob Pringle, and Grigoris J Karakoulas. Reinforcement
learning for true adaptive traffic signal control. Journal of Transportation
Engineering, 129(3):278–285, 2003.
[2] S Sheik Mohammed Ali, Boby George, Lelitha Vanajakshi, and
Jayashankar Venkatraman. A multiple inductive loop vehicle detection
system for heterogeneous and lane-less traffic. IEEE Transactions on
Instrumentation and Measurement, 61(5):1353–1360, 2011.
[3] Itamar Arel, Cong Liu, Tom Urbanik, and Airton G Kohls. Reinforcement
learning-based multi-agent system for network traffic signal
control. IET Intelligent Transport Systems, 4(2):128–135, 2010.
[4] PG Balaji, X German, and Dipti Srinivasan. Urban traffic signal control
using reinforcement learning agents. IET Intelligent Transport Systems,
4(3):177–188, 2010.
[5] Federico Barrero, Jean A. Guevara, Enrique Vargas, Sergio Toral, and
Manuel Vargas. Networked transducers in intelligent transportation systems
based on the ieee 1451 standard. Computer Standards Interfaces,
36(2):300–311, 2014.
[6] Yit Kwong Chin, Nurmin Bolong, Aroland Kiring, Soo Siang Yang,
and Kenneth Tze Kin Teo. Q-learning based traffic optimization in
management of signal timing plan. International Journal of Simulation,
Systems, Science & Technology, 12(3):29–35, 2011.
[7] Ali Çivril and Malik Magdon-Ismail. On selecting a maximum volume
sub-matrix of a matrix and related problems. Theoretical Computer
Science, 410(47-49):4801–4811, 2009.
[8] Seung-Bae Cools, Carlos Gershenson, and Bart D’Hooghe. Selforganizing
traffic lights: A realistic simulation. In Advances in applied
self-organizing systems, pages 45–55. Springer, 2013.
[9] M. Co¸skun, A. Baggag, and S. Chawla. Deep reinforcement learning
for traffic light optimization. In 2018 IEEE International Conference on
Data Mining Workshops (ICDMW), pages 564–571, 2018.
[10] Francois Dion, Hesham Rakha, and Youn-Soo Kang. Comparison of
delay estimates at under-saturated and over-saturated pre-timed signalized
intersections. Transportation Research Part B: Methodological, 38(2):99–122, 2004.
[11] Samah El-Tantawy, Baher Abdulhai, and Hossam Abdelgawad. Multiagent
reinforcement learning for integrated network of adaptive traffic
signal controllers (marlin-atsc): methodology and large-scale application
on downtown toronto. IEEE Transactions on Intelligent Transportation
Systems, 14(3):1140–1150, 2013.
[12] Sébastien Faye, Claude Chaudet, and Isabelle Demeure. A distributed
algorithm for multiple intersections adaptive traffic lights control using
a wireless sensor networks. In Proceedings of the First Workshop on
Urban Networking, UrbaNe ’12, page 13–18, New York, NY, USA,
2012. Association for Computing Machinery.
[13] Akshay Gadde, Aamir Anis, and Antonio Ortega. Active semisupervised
learning using sampling theory for graph signals. In Proceedings
of the 20th ACM SIGKDD international conference on Knowledge
discovery and data mining, pages 492–501, 2014.
[14] D. Gregor, S. Toral, T. Ariza, F. Barrero, R. Gregor, J. Rodas, and
M. Arzamendia. A methodology for structured ontology construction
applied to intelligent transportation systems. Computer Standards
Interfaces, 47:108–119, 2016.
[15] Andrew Guillory and Jeff A Bilmes. Label selection on graphs. In
Advances in Neural Information Processing Systems, pages 691–699,
2009.
[16] Ashley Hill, Antonin Raffin, Maximilian Ernestus, Adam Gleave, Anssi
Kanervisto, Rene Traore, Prafulla Dhariwal, Christopher Hesse, Oleg
Klimov, Alex Nichol, Matthias Plappert, Alec Radford, John Schulman,
Szymon Sidor, and Yuhuai Wu. Stable baselines. https://github.com/hilla/
stable-baselines, 2018.
[17] Waris Hooda, Pradeep Kumar Yadav, Amogh Bhole, and Deptii D.
Chaudhari. An image processing approach to intelligent traffic management
system. In Proceedings of the Second International Conference on
Information and Communication Technology for Competitive Strategies,
ICTCS ’16, New York, NY, USA, 2016. Association for Computing
Machinery.
[18] INRIX. Home.
[19] Yoichiro Iwasaki. Image processing system to measure vehicular queues
and an adaptive traffic signal control by using the information of the
queues. Computer Standards Interfaces, 20(6):444, 1999.
[20] Junteng Jia, Michael T Schaub, Santiago Segarra, and Austin R Benson.
Graph-based semi-supervised & active learning for edge flows. arXiv
preprint arXiv:1905.07451, 2019.
[21] Lior Kuyer, Shimon Whiteson, Bram Bakker, and Nikos Vlassis. Multiagent
reinforcement learning for urban traffic control using coordination
graphs. In Joint European Conference on Machine Learning and
Knowledge Discovery in Databases, pages 656–671. Springer, 2008.
[22] Ninad Lanke and Sheetal Koul. Smart traffic management system.
International Journal of Computer Applications, 75(7), 2013.
[23] Pablo Alvarez Lopez, Michael Behrisch, Laura Bieker-Walz, Jakob Erdmann,
Yun-Pang Flötteröd, Robert Hilbrich, Leonhard Lücken, Johannes
Rummel, Peter Wagner, and Evamarie Wießner. Microscopic traffic
simulation using sumo. In The 21st IEEE International Conference
on Intelligent Transportation Systems. IEEE, 2018.
[24] Patrick Mannion, Jim Duggan, and Enda Howley. An experimental
review of reinforcement learning algorithms for adaptive traffic signal
control. In Autonomic Road Transport Support Systems, pages 47–66.
Springer, 2016.
[25] Alan J Miller. Settings for fixed-cycle traffic signals. Journal of the
Operational Research Society, 14(4):373–386, 1963.
[26] Volodymyr Mnih, Adrià Puigdomènech Badia, Mehdi Mirza, Alex
Graves, Timothy P. Lillicrap, Tim Harley, David Silver, and Koray
Kavukcuoglu. Asynchronous methods for deep reinforcement learning,
2016.
[27] Hsin-Hung Pan, Shu-Ching Wang, and Kuo-Qin Yan. An integrated
data exchange platform for intelligent transportation systems. Computer
Standards Interfaces, 36(3):657–671, 2014.
[28] Isaac Porche and Stéphane Lafortune. Adaptive look-ahead optimization
of traffic signals. Journal of Intelligent Transportation System, 4(3-
4):209–254, 1999.
[29] I. Román, G. Madinabeitia, L. Jimenez, G.A. Molina, and J.A. Ternero.
Experiences applying rm-odp principles and techniques to intelligent
transportation system architectures. Computer Standards Interfaces,
35(3):338–347, 2013. RM-ODP: Foundations, Experience and Applications.
[30] John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg
Klimov. Proximal policy optimization algorithms, 2017.
[31] Brian L Smith and Michael J Demetsky. Short-term traffic flow
prediction: neural network approach. Transportation Research Record,
(1453), 1994.
[32] S.L. Toral, F. Barrero, F. Cortés, and D. Gregor. Analysis of embedded
corba middleware performance on urban distributed transportation
equipments. Computer Standards Interfaces, 35(1):150–157, 2013.
[33] Elise Van der Pol and Frans A Oliehoek. Coordinated deep reinforcement
learners for traffic light control. Proceedings of Learning, Inference
and Control of Multi-Agent Systems (at NIPS 2016), 2016.
[34] Fo Vo Webster. Traffic signal settings. Technical report, 1958.
[35] Hua Wei, Nan Xu, Huichu Zhang, Guanjie Zheng, Xinshi Zang, Chacha
Chen, Weinan Zhang, Yanmin Zhu, Kai Xu, and Zhenhui Li. Colight:
Learning network-level cooperation for traffic signal control. In Proceedings
of the 28th ACM International Conference on Information and
Knowledge Management, pages 1913–1922, 2019.
[36] Hua Wei, Guanjie Zheng, Vikash Gayah, and Zhenhui Li. Recent
advances in reinforcement learning for traffic signal control: A survey
of models and evaluation. ACM SIGKDD Explorations Newsletter,
22(2):12–18, 2021.
[37] Hua Wei, Guanjie Zheng, Huaxiu Yao, and Zhenhui Li. Intellilight:
A reinforcement learning approach for intelligent traffic light control.
In Proceedings of the 24th ACM SIGKDD International Conference on
Knowledge Discovery & Data Mining, pages 2496–2505. ACM, 2018.
[38] MA Wiering. Multi-agent reinforcement learning for traffic light control.
In Machine Learning: Proceedings of the Seventeenth International
Conference (ICML’2000), pages 1151–1158, 2000.
[39] Guanjie Zheng, Yuanhao Xiong, Xinshi Zang, Jie Feng, Hua Wei,
Huichu Zhang, Yong Li, Kai Xu, and Zhenhui Li. Learning phase
competition for traffic signal control. arXiv preprint arXiv:1905.04722,
2019.