<  Back to the Polytechnique Montréal portal

Maintenance planning for bridges using hierarchical reinforcement learning

Zachary Hamida and James Alexandre Goulet

Paper (2023)

Open Acess document in PolyPublie and at official publisher
[img]
Preview
Open Access to the full text of this document
Published Version
Terms of Use: Creative Commons Attribution Non-commercial Share Alike
Download (2MB)
Show abstract
Hide abstract

Abstract

This paper presents a hierarchical deep RL framework for maintenance planning on bridges. The proposed HRL framework provides advantages in scalability, and interpretability by allowing to visualize the decision boundaries of policies. The RL environment in this study is based on state-space models (SSM), which enables including the deterioration speed alongside the condition in the decision-making analyses. The performance of the proposed approach is evaluated by learning a maintenance policy for the beams structural category within a bridge in the Quebec province, Canada.

Department: Department of Civil, Geological and Mining Engineering
Funders: Ministère des transports du Québec (MTQ)
PolyPublie URL: https://publications.polymtl.ca/57349/
Conference Title: 14th International Conference on Applications of Statistics and Probability in Civil Engineering (ICASP14)
Conference Location: Dublin, Ireland
Conference Date(s): 2023-07-09 - 2023-07-13
Publisher: Trinity College Dublin
Official URL: http://hdl.handle.net/2262/103207
Date Deposited: 08 Feb 2024 10:25
Last Modified: 27 Apr 2024 19:43
Cite in APA 7: Hamida, Z., & Goulet, J. A. (2023, July). Maintenance planning for bridges using hierarchical reinforcement learning [Paper]. 14th International Conference on Applications of Statistics and Probability in Civil Engineering (ICASP14), Dublin, Ireland (8 pages). http://hdl.handle.net/2262/103207

Statistics

Total downloads

Downloads per month in the last year

Origin of downloads

Repository Staff Only

View Item View Item