File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: A reinforcement learning framework for the adaptive routing problem in stochastic time-dependent network

TitleA reinforcement learning framework for the adaptive routing problem in stochastic time-dependent network
Authors
KeywordsTree-based function approximation
Adaptive routing
Q learning
Reinforcement learning
Fitted Q iteration
Issue Date2018
Citation
Transportation Research Part C: Emerging Technologies, 2018, v. 93, p. 179-197 How to Cite?
Abstract© 2018 Elsevier Ltd Most previous work in addressing the adaptive routing problem in stochastic and time-dependent (STD) network has been focusing on developing parametric models to reflect the network dynamics and designing efficient algorithms to solve these models. However, strong assumptions need to be made in the models and some algorithms also suffer from the curse of dimensionality. In this paper, we examine the application of Reinforcement Learning as a non-parametric model-free method to solve the problem. Both the online Q learning method for discrete state space and the offline fitted Q iteration algorithm for continuous state space are discussed. With a small case study on a mid-sized network, we demonstrate the significant advantages of using Reinforcement Learning to solve for the optimal routing policy over traditional stochastic dynamic programming method. And the fitted Q iteration algorithm combined with tree-based function approximation is shown to outperform other methods especially during peak demand periods.
Persistent Identifierhttp://hdl.handle.net/10722/296176
ISSN
2023 Impact Factor: 7.6
2023 SCImago Journal Rankings: 2.860
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorMao, Chao-
dc.contributor.authorShen, Zuojun-
dc.date.accessioned2021-02-11T04:53:00Z-
dc.date.available2021-02-11T04:53:00Z-
dc.date.issued2018-
dc.identifier.citationTransportation Research Part C: Emerging Technologies, 2018, v. 93, p. 179-197-
dc.identifier.issn0968-090X-
dc.identifier.urihttp://hdl.handle.net/10722/296176-
dc.description.abstract© 2018 Elsevier Ltd Most previous work in addressing the adaptive routing problem in stochastic and time-dependent (STD) network has been focusing on developing parametric models to reflect the network dynamics and designing efficient algorithms to solve these models. However, strong assumptions need to be made in the models and some algorithms also suffer from the curse of dimensionality. In this paper, we examine the application of Reinforcement Learning as a non-parametric model-free method to solve the problem. Both the online Q learning method for discrete state space and the offline fitted Q iteration algorithm for continuous state space are discussed. With a small case study on a mid-sized network, we demonstrate the significant advantages of using Reinforcement Learning to solve for the optimal routing policy over traditional stochastic dynamic programming method. And the fitted Q iteration algorithm combined with tree-based function approximation is shown to outperform other methods especially during peak demand periods.-
dc.languageeng-
dc.relation.ispartofTransportation Research Part C: Emerging Technologies-
dc.subjectTree-based function approximation-
dc.subjectAdaptive routing-
dc.subjectQ learning-
dc.subjectReinforcement learning-
dc.subjectFitted Q iteration-
dc.titleA reinforcement learning framework for the adaptive routing problem in stochastic time-dependent network-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.trc.2018.06.001-
dc.identifier.scopuseid_2-s2.0-85048325293-
dc.identifier.volume93-
dc.identifier.spage179-
dc.identifier.epage197-
dc.identifier.isiWOS:000442173400011-
dc.identifier.issnl0968-090X-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats