Surrogate Assisted Monte Carlo Tree Search in Combinatorial Optimization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914715429502976 |
|---|---|
| author | Amiri, Saeid Zehtabi, Parisa Dervovic, Danial Cashmore, Michael |
| author_facet | Amiri, Saeid Zehtabi, Parisa Dervovic, Danial Cashmore, Michael |
| contents | Industries frequently adjust their facilities network by opening new branches in promising areas and closing branches in areas where they expect low profits. In this paper, we examine a particular class of facility location problems. Our objective is to minimize the loss of sales resulting from the removal of several retail stores. However, estimating sales accurately is expensive and time-consuming. To overcome this challenge, we leverage Monte Carlo Tree Search (MCTS) assisted by a surrogate model that computes evaluations faster. Results suggest that MCTS supported by a fast surrogate function can generate solutions faster while maintaining a consistent solution compared to MCTS that does not benefit from the surrogate function. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_09925 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Surrogate Assisted Monte Carlo Tree Search in Combinatorial Optimization Amiri, Saeid Zehtabi, Parisa Dervovic, Danial Cashmore, Michael Artificial Intelligence Industries frequently adjust their facilities network by opening new branches in promising areas and closing branches in areas where they expect low profits. In this paper, we examine a particular class of facility location problems. Our objective is to minimize the loss of sales resulting from the removal of several retail stores. However, estimating sales accurately is expensive and time-consuming. To overcome this challenge, we leverage Monte Carlo Tree Search (MCTS) assisted by a surrogate model that computes evaluations faster. Results suggest that MCTS supported by a fast surrogate function can generate solutions faster while maintaining a consistent solution compared to MCTS that does not benefit from the surrogate function. |
| title | Surrogate Assisted Monte Carlo Tree Search in Combinatorial Optimization |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2403.09925 |