Deep Reinforcement Learning Guided Improvement Heuristic for Job Shop Scheduling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917589273280512 |
|---|---|
| author | Zhang, Cong Cao, Zhiguang Song, Wen Wu, Yaoxin Zhang, Jie |
| author_facet | Zhang, Cong Cao, Zhiguang Song, Wen Wu, Yaoxin Zhang, Jie |
| contents | Recent studies in using deep reinforcement learning (DRL) to solve Job-shop scheduling problems (JSSP) focus on construction heuristics. However, their performance is still far from optimality, mainly because the underlying graph representation scheme is unsuitable for modelling partial solutions at each construction step. This paper proposes a novel DRL-guided improvement heuristic for solving JSSP, where graph representation is employed to encode complete solutions. We design a Graph Neural-Network-based representation scheme, consisting of two modules to effectively capture the information of dynamic topology and different types of nodes in graphs encountered during the improvement process. To speed up solution evaluation during improvement, we present a novel message-passing mechanism that can evaluate multiple solutions simultaneously. We prove that the computational complexity of our method scales linearly with problem size. Experiments on classic benchmarks show that the improvement policy learned by our method outperforms state-of-the-art DRL-based methods by a large margin. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2211_10936 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Deep Reinforcement Learning Guided Improvement Heuristic for Job Shop Scheduling Zhang, Cong Cao, Zhiguang Song, Wen Wu, Yaoxin Zhang, Jie Machine Learning Artificial Intelligence Recent studies in using deep reinforcement learning (DRL) to solve Job-shop scheduling problems (JSSP) focus on construction heuristics. However, their performance is still far from optimality, mainly because the underlying graph representation scheme is unsuitable for modelling partial solutions at each construction step. This paper proposes a novel DRL-guided improvement heuristic for solving JSSP, where graph representation is employed to encode complete solutions. We design a Graph Neural-Network-based representation scheme, consisting of two modules to effectively capture the information of dynamic topology and different types of nodes in graphs encountered during the improvement process. To speed up solution evaluation during improvement, we present a novel message-passing mechanism that can evaluate multiple solutions simultaneously. We prove that the computational complexity of our method scales linearly with problem size. Experiments on classic benchmarks show that the improvement policy learned by our method outperforms state-of-the-art DRL-based methods by a large margin. |
| title | Deep Reinforcement Learning Guided Improvement Heuristic for Job Shop Scheduling |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2211.10936 |