A review of methods to model route choice behavior of bicyclists: Inverse reinforcement learning in spatial context and recursive logit

Thomas Koch, Elenna Dugundji

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

Used for route choice modeling by the transportation research community, recursive logit is a form of inverse reinforcement learning, the field of learning an agent's objective by observing it's behavior. By solving a large-scale system of linear equations it allows estimation of an optimal (negative) reward function in a computationally efficient way that performs for large networks and a large number of observations. In this paper we review examples of IRL models applied to real world travel trajectories and look at some of the challenges with recursive logit for modeling bicycle route choice in the city center area of Amsterdam.

Original languageEnglish
Title of host publicationProceedings of the 3rd ACM SIGSPATIAL International Workshop on GeoSpatial Simulation, GeoSim 2020
EditorsTaylor Anderson, Joon-Seok Kim, Ashwin Shashidharan
PublisherAssociation for Computing Machinery, Inc
Pages30-37
Number of pages8
ISBN (Electronic)9781450381611
DOIs
Publication statusPublished - 3 Nov 2020
Event3rd ACM SIGSPATIAL International Workshop on GeoSpatial Simulation, GeoSim 2020 - Seattle, United States
Duration: 3 Nov 2020 → …

Publication series

NameProceedings of the 3rd ACM SIGSPATIAL International Workshop on GeoSpatial Simulation, GeoSim 2020

Conference

Conference3rd ACM SIGSPATIAL International Workshop on GeoSpatial Simulation, GeoSim 2020
Country/TerritoryUnited States
CitySeattle
Period3/11/20 → …

Keywords

  • bicycle route behavior
  • dynamic discrete choice
  • dynamic programming
  • GPS trajectory
  • inverse reinforcement learning
  • markov decision process
  • maximum entropy
  • recursive logit
  • route choice modeling

Fingerprint

Dive into the research topics of 'A review of methods to model route choice behavior of bicyclists: Inverse reinforcement learning in spatial context and recursive logit'. Together they form a unique fingerprint.

Cite this