Document Server@UHasselt >
Research >
Research publications >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/9538

Title: Implementing an Improved Reinforcement Learning Algorithm for the Simulation of Weekly Activity-Travel Sequences
Authors: VANHULSEL, Marlies
WETS, Geert
Issue Date: 2008
Citation: Transportation Research Board 87th Annual Meeting, 87, Washington, U.S.A, 13-17 January 2008.
Abstract: Recently, within the area of activity-based travel demand modeling there is a general tendency to enhance the realism of these models by incorporating dynamics based on learning and adaptation processes. The research presented here attempts at contributing to the current state of the art by formulating a framework for the simulation of individual activity-travel patterns. To this end, the current research redesigns an existing reinforcement learning technique by adding a regression-tree function approximator. This artifice enables the Q-learning algorithm not only to consider more explanatory and decision variables, but also to handle a larger granularity of these dimensions. In addition, the reward function underlying the Q-learning process is drawn up carefully based on activity attributes rather than activity type. For the purpose of testing the applicability of the proposed improvements, a prototype model is implemented and applied to real-world data. The prototype model proves to learn weekly activity-travel patterns rather quickly, requiring only a limited amount of memory. Additionally, in order to validate the suggested approach, the simulated weekly activity-travel sequences are compared to the observed ones by assessing the dissimilarity based on a number of distance measures.
URI: http://hdl.handle.net/1942/9538
Category: C2
Type: Conference Material
Appears in Collections: Research publications

Files in This Item:

Description SizeFormat
Preprint2.92 MBAdobe PDF

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.