Large-scale Urban Facility Location Selection with Knowledge-informed Reinforcement Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916384377667584 |
|---|---|
| author | Su, Hongyuan Zheng, Yu Ding, Jingtao Jin, Depeng Li, Yong |
| author_facet | Su, Hongyuan Zheng, Yu Ding, Jingtao Jin, Depeng Li, Yong |
| contents | The facility location problem (FLP) is a classical combinatorial optimization challenge aimed at strategically laying out facilities to maximize their accessibility. In this paper, we propose a reinforcement learning method tailored to solve large-scale urban FLP, capable of producing near-optimal solutions at superfast inference speed. We distill the essential swap operation from local search, and simulate it by intelligently selecting edges on a graph of urban regions, guided by a knowledge-informed graph neural network, thus sidestepping the need for heavy computation of local search. Extensive experiments on four US cities with different geospatial conditions demonstrate that our approach can achieve comparable performance to commercial solvers with less than 5\% accessibility loss, while displaying up to 1000 times speedup. We deploy our model as an online geospatial application at https://huggingface.co/spaces/randommmm/MFLP. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_01588 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Large-scale Urban Facility Location Selection with Knowledge-informed Reinforcement Learning Su, Hongyuan Zheng, Yu Ding, Jingtao Jin, Depeng Li, Yong Machine Learning Artificial Intelligence Computers and Society 68T20 The facility location problem (FLP) is a classical combinatorial optimization challenge aimed at strategically laying out facilities to maximize their accessibility. In this paper, we propose a reinforcement learning method tailored to solve large-scale urban FLP, capable of producing near-optimal solutions at superfast inference speed. We distill the essential swap operation from local search, and simulate it by intelligently selecting edges on a graph of urban regions, guided by a knowledge-informed graph neural network, thus sidestepping the need for heavy computation of local search. Extensive experiments on four US cities with different geospatial conditions demonstrate that our approach can achieve comparable performance to commercial solvers with less than 5\% accessibility loss, while displaying up to 1000 times speedup. We deploy our model as an online geospatial application at https://huggingface.co/spaces/randommmm/MFLP. |
| title | Large-scale Urban Facility Location Selection with Knowledge-informed Reinforcement Learning |
| topic | Machine Learning Artificial Intelligence Computers and Society 68T20 |
| url | https://arxiv.org/abs/2409.01588 |