Citation

Gabel T, Riedmiller M. Int. J. Traffic Transp. Eng. (Rosemead, Calif.) 2013; 1(4): 67-76.

Copyright

(Copyright © 2013, Scientific and Academic Publishing)

DOI

unavailable

PMID

unavailable

Abstract

The optimization of traffic flow on roads and highways of modern industrialized countries is key to their economic growth and success. Besides, the reduction of traffic congestions and jams is also desirable from an ecological point of view as it yields a contribution to climate protection. In this article, we stick to a microscopic traffic simulation model and interpret the task of traffic flow optimization as a multi-agent learning problem. In so doing, we attach simple, adaptive agents to each of the vehicles and make them learn, using a distributed variant of model-free reinforcement learning, a cooperative driving behavior that is jointly optimal and aims at the prevention of traffic jams. Our approach is evaluated in a series of simulation experiments that emphasize that the substitution of selfish human behavior in traffic by the learned driving policies of the agents can result in substantial improvements in the quality of traffic flow.

IMPORTANT: The "Web of Trust" rates this journal publisher's website as dangerous because the few ratings it has received are from those who object to the publishers fee for publication and author solicitation practices. SafetyLit risks our own site being blocked by WoT if we link to a dangerous site. Therefore, we cannot place this article's DOI in the "Find Full Text" utility. However, you can find the full text of this article bygoing to

http://dx.doi.org

and placing "10.5923/j.ijtte.20120104.03" within the search field.

While this publisher may or may not use predatory solicitation practices; it concerns SafetyLit that a few disgruntled raters can effectively supress availability of information to all. What if the raters choose to slam a website because of disagreements with political or social viewpoints?