A Sliding-Window-Based Reinforcement Learning for Dynamic Assembly Flow Shop Scheduling with Multi-Product Delivery
Quick Answer
The proposed Sliding-Window-Based Reinforcement Learning (SWRL) framework effectively addresses real-time scheduling challenges in hybrid manufacturing systems, achieving significant tardiness reductions over classical methods and existing deep reinforcement learning approaches.
Quick Take
The proposed Sliding-Window-Based Reinforcement Learning (SWRL) framework effectively addresses real-time scheduling challenges in hybrid manufacturing systems, achieving significant tardiness reductions over classical methods and existing deep reinforcement learning approaches. Experiments with a home appliance manufacturer demonstrate SWRL's robust performance across various resource configurations and order loads.
Key Points
- SWRL integrates a sliding-window filtering mechanism to prioritize critical operations.
- The framework captures dual-layer kitting structure using a heterogeneous graph-based MDP.
- Experiments show consistent tardiness reductions compared to classical dispatching rules.
- SWRL adapts to changing action spaces under variable topologies.
- Robust performance across varying resource configurations and order loads was demonstrated.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Multi-product kitting delivery imposes significant challenges for real-time scheduling in hybrid manufacturing systems that integrate processing and assembly, as dynamic order arrivals simultaneously alter supply dependencies and the set of feasible job-machine assignments. This paper proposes a sliding-window-based reinforcement learning (SWRL) framework for end-to-end online scheduling in the flexible assembly flow shop scheduling problem with complex kitting constraints. The problem is formulated as a heterogeneous graph-based Markov decision process that captures the dual-layer kitting structure and the tail-product bottleneck dynamics that produce a sparse reward landscape. To address the resulting challenges, SWRL integrates a sliding-window filtering mechanism that filters inactive nodes and prioritizes kitting-critical operations, a spatiotemporal graph encoding network that tracks bottleneck shifts across consecutive decision states, and a dynamic action mapping module with a constrained waiting strategy that adapts to the changing action space under variable topologies. Experiments on real-world instances from a home appliance manufacturer demonstrate that SWRL achieves consistent tardiness reductions over classical dispatching rules and existing deep reinforcement learning methods, and exhibits robust performance across varying resource configurations, order loads, and arrival concentrations.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.02941 [cs.AI] |
| (or arXiv:2607.02941v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.02941 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Junhao Qiu [view email]
[v1]
Fri, 3 Jul 2026 04:27:52 UTC (1,135 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Procedural Memory Distillation: Online Reflection for Self-Improving Language Models
Procedural Memory Distillation (PMD) enhances reinforcement learning by converting cross-episode signals into reusable memory, improving Qwen3-8B and OLMo3-Instruct-7B models by 3.8-5.5% on SCIKNOWEVAL and 7.9-13.6% on . The co-evolution of policy and memory allows for more effective self-supervision, demonstrating significant performance gains when both components are active.