Table of Contents Author Guidelines Submit a Manuscript
Mathematical Problems in Engineering
Volume 2014, Article ID 951367, 11 pages
http://dx.doi.org/10.1155/2014/951367
Research Article

Multiagent-Based Simulation of Temporal-Spatial Characteristics of Activity-Travel Patterns Using Interactive Reinforcement Learning

1School of Transportation, Southeast University, Si Pai Lou No. 2, Nanjing 210096, China
2Department of Civil and Environment Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139-4307, USA

Received 6 September 2013; Revised 6 November 2013; Accepted 9 December 2013; Published 30 January 2014

Academic Editor: Geert Wets

Copyright © 2014 Min Yang et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

We propose a multiagent-based reinforcement learning algorithm, in which the interactions between travelers and the environment are considered to simulate temporal-spatial characteristics of activity-travel patterns in a city. Road congestion degree is added to the reinforcement learning algorithm as a medium that passes the influence of one traveler’s decision to others. Meanwhile, the agents used in the algorithm are initialized from typical activity patterns extracted from the travel survey diary data of Shangyu city in China. In the simulation, both macroscopic activity-travel characteristics such as traffic flow spatial-temporal distribution and microscopic characteristics such as activity-travel schedules of each agent are obtained. Comparing the simulation results with the survey data, we find that deviation of the peak-hour traffic flow is less than 5%, while the correlation of the simulated versus survey location choice distribution is over 0.9.