Agent-based traffic management and reinforcement learning in congested intersection network.

Medina, Juan C.; Benekohal, Rahim F.

i

Agent-based traffic management and reinforcement learning in congested intersection network.

2012-08-01
By Medina, Juan C. ; Benekohal, Rahim F.

File Language:

English

Details

Creators:

Medina, Juan C. ; Benekohal, Rahim F.
Corporate Creators:

University of Illinois at Urbana-Champaign
Corporate Contributors:

United States. Dept. of Transportation. Research and Innovative Technology Administration
Subject/TRT Terms:
Publication/ Report Number:

072IY03
Resource Type:

Tech Report
Geographical Coverage:

United States
Corporate Publisher:

NEXTRANS Center (U.S.)
NTL Classification:

NTL-OPERATIONS AND TRAFFIC CONTROLS-Congestion ; NTL-OPERATIONS AND TRAFFIC CONTROLS-Traffic Control Devices
Abstract:

This study evaluates the performance of traffic control systems based on reinforcement learning (RL), also called approximate dynamic programming (ADP). Two algorithms have been selected for testing: 1) Q-learning and 2) approximate dynamic programming (ADP) with a post-decision state variable. The algorithms were tested in increasingly complex scenarios, from an oversaturated isolated intersection, to an arterial in undersaturated conditions, to a 2x5 network in both undersaturation and oversaturation, and finally to a 4x5 network in oversaturation with even and uneven directional demands. Potential benefits of these algorithms include signal systems that not only quickly respond to the actual conditions found in the field, but also learn about them and truly adapt through flexible cycle-free strategies. Moreover, these signal systems are decentralized, providing greater scalability and lower vulnerability at the network level.
Format:

PDF
Download URL:

https://rosap.ntl.bts.gov/view/dot/23341/dot_23341_DS1.pdf
File Type:

[PDF - 2.06 MB]
Collection(s):

University Transportation Centers ; US Transportation Collection
Main Document Checksum:

urn:sha-512:067ed2931d0e32f61f17ede8fe15034ed8106daa5f029c2fe9b5b1fa683d4fb9ac4e61dc40fc7bfc35258a22c8bdd46533697ac574deffb082bc5558cb279dc7

File Language:

English

ON THIS PAGE

Details

Found an issue?

Send us an email at:

publishinghd@cdc.gov

ROSA P serves as an archival repository of USDOT-published products including scientific findings, journal articles, guidelines, recommendations, or other information authored or co-authored by USDOT or funded partners. As a repository, ROSA P retains documents in their original published format to ensure public access to scientific information.