Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2511.11870 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914159022571520 |
|---|---|
| author | Agyeman, Bernard T. Li, Zhe Mitrai, Ilias Daoutidis, Prodromos |
| author_facet | Agyeman, Bernard T. Li, Zhe Mitrai, Ilias Daoutidis, Prodromos |
| contents | This work introduces an end-to-end graph-based agent for accelerating the computational efficiency of Benders Decomposition. The agent's policy is parameterized by a graph neural network which takes as input a bipartite graph representation of the master problem and proposes a candidate solution. The agent is trained using a two-stage approach that combines imitation (IL) and reinforcement learning (RL). IL is used to mimic a solver and obtain a warm-start policy which is then finetuned using RL with a reward signal that balances feasibility and computational efficiency. We augment the agent with a verification mechanism that checks the agent's prediction for feasibility and solution quality. The framework is evaluated in two case studies: (i) an illustrative mixed-integer nonlinear program, where it reduces the solution time by 42% without loss of solution quality, and (ii) a closed-loop irrigation scheduling problem, where it achieves a 23% time reduction without compromising water use efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_11870 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Graph-Based Imitation and Reinforcement Learning for Efficient Benders Decomposition Agyeman, Bernard T. Li, Zhe Mitrai, Ilias Daoutidis, Prodromos Optimization and Control This work introduces an end-to-end graph-based agent for accelerating the computational efficiency of Benders Decomposition. The agent's policy is parameterized by a graph neural network which takes as input a bipartite graph representation of the master problem and proposes a candidate solution. The agent is trained using a two-stage approach that combines imitation (IL) and reinforcement learning (RL). IL is used to mimic a solver and obtain a warm-start policy which is then finetuned using RL with a reward signal that balances feasibility and computational efficiency. We augment the agent with a verification mechanism that checks the agent's prediction for feasibility and solution quality. The framework is evaluated in two case studies: (i) an illustrative mixed-integer nonlinear program, where it reduces the solution time by 42% without loss of solution quality, and (ii) a closed-loop irrigation scheduling problem, where it achieves a 23% time reduction without compromising water use efficiency. |
| title | Graph-Based Imitation and Reinforcement Learning for Efficient Benders Decomposition |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2511.11870 |