Online Large-Scale Taxi Assignment: Optimization and Learning
We propose a solution method for online vehicle routing, which integrates a machine learning routine to improve tours’ quality. Our optimization model is based on the Bertsimas et al. (2019) re-optimization approach. Two separate routines are developed. The first one uses a neural network to produce...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Findings Press
2023-05-01
|
| Series: | Findings |
| Online Access: | https://doi.org/10.32866/001c.74765 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850043749746343936 |
|---|---|
| author | Omar Rifki Thierry Garaix |
| author_facet | Omar Rifki Thierry Garaix |
| author_sort | Omar Rifki |
| collection | DOAJ |
| description | We propose a solution method for online vehicle routing, which integrates a machine learning routine to improve tours’ quality. Our optimization model is based on the Bertsimas et al. (2019) re-optimization approach. Two separate routines are developed. The first one uses a neural network to produce realistic pick-up times for the customers to serve. The second one relies on Q-learning in addition to random walks for the construction of the backbone graph corresponding to the instance problem of each time step. The second routine gives improved results compared to the original approach. |
| format | Article |
| id | doaj-art-0dc69c0815594580b4a769d7e2f35c78 |
| institution | DOAJ |
| issn | 2652-8800 |
| language | English |
| publishDate | 2023-05-01 |
| publisher | Findings Press |
| record_format | Article |
| series | Findings |
| spelling | doaj-art-0dc69c0815594580b4a769d7e2f35c782025-08-20T02:55:09ZengFindings PressFindings2652-88002023-05-0110.32866/001c.74765Online Large-Scale Taxi Assignment: Optimization and LearningOmar RifkiThierry GaraixWe propose a solution method for online vehicle routing, which integrates a machine learning routine to improve tours’ quality. Our optimization model is based on the Bertsimas et al. (2019) re-optimization approach. Two separate routines are developed. The first one uses a neural network to produce realistic pick-up times for the customers to serve. The second one relies on Q-learning in addition to random walks for the construction of the backbone graph corresponding to the instance problem of each time step. The second routine gives improved results compared to the original approach.https://doi.org/10.32866/001c.74765 |
| spellingShingle | Omar Rifki Thierry Garaix Online Large-Scale Taxi Assignment: Optimization and Learning Findings |
| title | Online Large-Scale Taxi Assignment: Optimization and Learning |
| title_full | Online Large-Scale Taxi Assignment: Optimization and Learning |
| title_fullStr | Online Large-Scale Taxi Assignment: Optimization and Learning |
| title_full_unstemmed | Online Large-Scale Taxi Assignment: Optimization and Learning |
| title_short | Online Large-Scale Taxi Assignment: Optimization and Learning |
| title_sort | online large scale taxi assignment optimization and learning |
| url | https://doi.org/10.32866/001c.74765 |
| work_keys_str_mv | AT omarrifki onlinelargescaletaxiassignmentoptimizationandlearning AT thierrygaraix onlinelargescaletaxiassignmentoptimizationandlearning |