Evaluating reinforcement learning state representations for adaptive traffic signal control

Reinforcement learning has shown potential for developing effective adaptive traffic signal controllers to reduce traffic congestion and improve mobility. Despite many successful research studies, few of these ideas have been implemented in practice. There remains uncertainty about what the requirements are in terms of data and sensors to actualize reinforcement learning traffic signal control. The authors seek to understand the data requirements and the performance differences in different state representations for reinforcement learning traffic signal control. They model three state representations, from low to high-resolution, and compare their performance using the asynchronous advantage actor-critic algorithm with neural network function approximation in simulation. Results show that low-resolution state representations (e.g., occupancy and average speed) perform almost identically to high-resolution state representations (e.g., individual vehicle position and speed). These results indicate implementing reinforcement learning traffic signal controllers may be possible with conventional sensors, such as loop detectors, and do not require sophisticated sensors, such as cameras or radar.

• Record URL:
  • https://doi.org/10.1016/j.procs.2018.04.008
• Record URL:
  • http://www.sciencedirect.com/science/article/pii/S1877050918303582
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/18770509
• Supplemental Notes:
  • © 2018 Wade Genders and Saiedeh Razavi. Published by Elsevier B.V. 9th International Conference on Ambient Systems, Networks and Technologies (ANT 2018).
• Authors:
  • Genders, Wade
  • Razavi, Saiedeh
• Publication Date: 2018

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References; Tables;
• Pagination: pp 26-33
• Serial:
  • Procedia Computer Science
  • Volume: 130
  • Issue Number: 0
  • Publisher: Elsevier
  • ISSN: 1877-0509
  • Serial URL: http://www.sciencedirect.com/science/journal/18770509
• Publication flags:

  Open Access (libre)

Subject/Index Terms

• TRT Terms: Adaptive control; Mobility; Neural networks; Traffic congestion; Traffic signal control systems
• Subject Areas: Highways; Operations and Traffic Management;

Filing Info

• Accession Number: 01676141
• Record Type: Publication
• Files: TRIS
• Created Date: Jul 26 2018 10:35AM