SLAB: Time-Lag-Aware Deep Reinforcement Learning for Flexible Job-Shop Scheduling in PPVC Module Factories
Abstract
Prefabricated prefinished volumetric construction (PPVC) builds room-sized modules in factories that operate as flexible job shops. A module waits 12 to 48 h after casting, waterproofing, and painting, while its station is free for other modules. Existing learned dispatchers release the next operation before this wait ends, so their plans need repair. This paper presents SLAB (Scheduling under time-Lags with an Admissible Bound), a decision process for dispatchers trained by deep reinforcement learning. Its transition releases a module only after its wait, and its reward is the decrease of a proven lower bound that includes the waits. Training on 10-module orders with halved waits also teaches the policy the station contention of larger orders. On three existing networks, repaired plans are 42% to 133% longer than the same network's schedules inside SLAB. On orders generated from Singapore's PPVC guidebook, one trained policy gives schedules 2.2% to 8.1% shorter than the shortest-processing-time rule at 10 to 80 modules. At 50 and 80 modules, it outperforms a time-lag memetic algorithm by 6.7% and 7.4% and constraint-programming search started from that rule's schedule and given 600 s by 6.6% and 7.6%. The memetic algorithm gives shorter schedules on orders of 10 modules, and the same search given 300 s on orders of 10 and 20 modules. A module factory can therefore train one dispatcher on small orders and run it without a solver on production batches of 50 to 80 modules.
Related
- Efficient Detailed Scheduling of Multiproduct Pipelines using Action-Decoupled Deep Reinforcement Learning
- BOLT: Multi-Bottleneck Bound-Guided Learning for Flexible Job-Shop Scheduling with Time Lags and Resource-Coupled Transport
- Integrating YOLOv8-based disaster detection with deep reinforcement learning for closed-loop UAV emergency response scheduling: A simulation study
- Graph-Convolutional Reinforcement Learning for Finite-Time Stabilization of a Chaotic Chua Circuit via Unified Flexible Terminal Sliding-Mode Control
- Optimization method for flexible scheduling of digital twin industrial loads based on load side potential elasticity
BibTeX
@misc{zhang2026slab,
title = {{SLAB: Time-Lag-Aware Deep Reinforcement Learning for Flexible Job-Shop Scheduling in PPVC Module Factories}},
author = {Ziheng Zhang and Dhivya Dharshini Kannan and Wei Zhang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2607.11725},
eprint = {2607.11725},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.11725},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - SLAB: Time-Lag-Aware Deep Reinforcement Learning for Flexible Job-Shop Scheduling in PPVC Module Factories
AU - Ziheng Zhang
AU - Dhivya Dharshini Kannan
AU - Wei Zhang
PY - 2026
DA - 2026/10/24
PB - arXiv
DO - 10.48550/arxiv.2607.11725
UR - https://arxiv.org/abs/2607.11725
AB - Prefabricated prefinished volumetric construction (PPVC) builds room-sized modules in factories that operate as flexible job shops. A module waits 12 to 48 h after casting, waterproofing, and painting, while its station is free for other modules. Existing learned dispatchers release the next operation before this wait ends, so their plans need repair. This paper presents SLAB (Scheduling under time-Lags with an Admissible Bound), a decision process for dispatchers trained by deep reinforcement learning. Its transition releases a module only after its wait, and its reward is the decrease of a proven lower bound that includes the waits. Training on 10-module orders with halved waits also teaches the policy the station contention of larger orders. On three existing networks, repaired plans are 42% to 133% longer than the same network's schedules inside SLAB. On orders generated from Singapore's PPVC guidebook, one trained policy gives schedules 2.2% to 8.1% shorter than the shortest-processing-time rule at 10 to 80 modules. At 50 and 80 modules, it outperforms a time-lag memetic algorithm by 6.7% and 7.4% and constraint-programming search started from that rule's schedule and given 600 s by 6.6% and 7.6%. The memetic algorithm gives shorter schedules on orders of 10 modules, and the same search given 300 s on orders of 10 and 20 modules. A module factory can therefore train one dispatcher on small orders and run it without a solver on production batches of 50 to 80 modules.
ER -