This study presents the application of XCS learning algorithm in simulating drivers' lane selection behaviour in microscopic simulation models of toll plazas. XCS is a special case of learning classifier systems, a machine learning technique that ties reinforcement learning (RL) and genetic algorithm. The proposed formulation translates an agent's lane selection decision into a learning problem, assuming that its ultimate objective is to reduce delay and crash risk. The agent is simulated without any notion of the outcome of its decisions. Through multiple learning episodes and the outcome of its actions, it learns the best policy to implement in a given network setting. A hypothetical toll plaza simulation network developed in Paramics simulation software is used to conduct experimental analyses. The results demonstrate that the agent's toll lane selection decision yields superior results in terms of delay and crash risk compared with those of minimum queue lane selection, minimum risk lane selection, random lane selection and multinomial probit model‐based lane selection behaviours. Although both the delay and crash risk objectives are not used simultaneously during learning, this study is intended as a proof of concept to demonstrate the feasibility of implementing RL algorithms in microscopic traffic simulation models.
Use of learning classifier systems in microscopic toll plaza simulation models
IET Intelligent Transport Systems ; 13 , 5 ; 860-869
2019-05-01
10 pages
Article (Journal)
Electronic Resource
English
XCS learning algorithm , random lane selection , learning classifier systems , implementing RL algorithms , Paramics simulation software , toll lane selection decision , drivers , road traffic , microscopic simulation models , traffic engineering computing , multiple learning episodes , learning problem , road vehicles , genetic algorithm , genetic algorithms , toll plazas , pattern classification , microscopic toll plaza simulation models , microscopic traffic simulation models , minimum queue lane selection , learning (artificial intelligence) , multinomial probit model‐based lane selection , hypothetical toll plaza simulation network , crash risk objectives , minimum risk lane selection , machine learning technique
Use of learning classifier systems in microscopic toll plaza simulation models
IET | 2019
|Developing Microscopic Integrated Freeway-Toll Plaza Model
British Library Conference Proceedings | 2005
|Developing Microscopic Toll Plaza and Toll Road Corridor Model with PARAMICS
Online Contents | 2008
|Developing Microscopic Toll Plaza and Toll Road Corridor Model with PARAMICS
Transportation Research Record | 2008
|