Sensitivity of reinforcement learning agents to aggregated sensor data in congested traffic networks

J. C. Medina, R. F. Benekohal

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Flexible signal timing operation with cycle-free and sequence-free strategies using reinforcement learning has been researched from different fields and applied to transportation networks. Such techniques naturally rely on accurate incoming data for optimal operation. However, the effect of imperfect information received by RL agents in a traffic environment has not been explored in detail and may provide further indication to whether they can be truly suitable for real-world applications. This paper studies this topic in the context of a congested traffic network, where RL agents receive aggregated loop detector data to make decisions, instead of directly observing activations from all vehicles. A case study shows the sensitivity of the agents' performance when data is aggregated to different levels. Aggregation levels are used as a method to represent imperfect information, and the performance of the system is used as an indicator to determine acceptable aggregation for the system to remain operational in oversaturated conditions.

Original languageEnglish (US)
Title of host publicationT and DI Congress 2014
Subtitle of host publicationPlanes, Trains, and Automobiles - Proceedings of the 2nd Transportation and Development Institute Congress
EditorsAmiy Varma, Geoffrey D. Gosling
PublisherAmerican Society of Civil Engineers
Pages719-726
Number of pages8
ISBN (Electronic)9780784413586
DOIs
StatePublished - Jan 1 2014
Event2nd Transportation and Development Institute Congress - Planes, Trains, and Automobiles: Connections to Future Developments, T and DI 2014 - Orlando, United States
Duration: Jun 8 2014Jun 11 2014

Publication series

NameT and DI Congress 2014: Planes, Trains, and Automobiles - Proceedings of the 2nd Transportation and Development Institute Congress

Other

Other2nd Transportation and Development Institute Congress - Planes, Trains, and Automobiles: Connections to Future Developments, T and DI 2014
CountryUnited States
CityOrlando
Period6/8/146/11/14

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Safety, Risk, Reliability and Quality
  • Mechanics of Materials

Fingerprint Dive into the research topics of 'Sensitivity of reinforcement learning agents to aggregated sensor data in congested traffic networks'. Together they form a unique fingerprint.

Cite this