Metraipolis › archive › dc_db0c3e29b421
Curriculum Learning with GNN-based Reinforcement Learning for Job Shop Scheduling — arXiv:2609.28085
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.28085
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T09:13:17.569Z
- SHA-256 of the archived text
507da97c4b1c5f74b79ecd4dd837e9254c314d418a0fb84db6b9c7623284735b- Stable URL of this page
https://metraipolis.com/documento/dc_db0c3e29b421
How to cite
Curriculum Learning with GNN-based Reinforcement Learning for Job Shop Scheduling — arXiv:2609.28085 — arXiv (en), https://arxiv.org/abs/2609.28085 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db0c3e29b421 (Metraipolis archive dc_db0c3e29b421, sha256 507da97c4b1c5f74b79ecd4dd837e9254c314d418a0fb84db6b9c7623284735b)
BibTeX
@misc{dcdb0c3e29b421,
title = {Curriculum Learning with GNN-based Reinforcement Learning for Job Shop Scheduling — arXiv:2609.28085},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.28085},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db0c3e29b421; sha256 507da97c4b1c5f74b79ecd4dd837e9254c314d418a0fb84db6b9c7623284735b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28085. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The job shop scheduling problem is a challenging combinatorial optimization problem, and recent reinforcement learning approaches using graph neural networks have shown promise for learning scheduling policies directly from problem instances. However, training on large instances remains computationally expensive, and generalization across instance sizes remains challenging. This paper studies curriculum learning for graph neural network-based reinforcement learning in the job shop scheduling problem by comparing it with single-size training across three target sizes: 20 x 20, 25 x 25, and 30 x 30. In the curriculum setting, the policy is first trained on smaller instances and then progressively adapted to larger target sizes, allowing scheduling behavior learned in earlier stages to support learning on larger instances. Models are evaluated on unseen instances from 8 x 8 to 30 x 30 using the optimality gap, considering both generalization across all evaluation sizes and specialization on the target size. Results show that curriculum learning consistently reduces wall-clock training time, with larger benefits as the target size increases. The strongest advantage is observed at 30 x 30, where curriculum learning reduces the mean optimality gap across all evaluation sizes by approximately 8.1 percentage points, reduces the target-size mean optimality gap by approximately 8.6 percentage points, and saves approximately 50 hours of training time. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.28085 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T08:13:26.745Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).