.png){kind=icon}
.png){kind=icon}
Return
A decomposition-based reinforcement learning approach for production and distribution integrated scheduling problem of perishable products
.png){kind=icon}
PRE
AI
Y
B
L
李
DOI：10.1016/j.swevo.2026.102478.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A decomposition-based RL framework is developed for integrated production and distribution scheduling of perishable products. • HLNS decomposes the integrated problem into vehicle-specific production scheduling subproblems. • A DDQN policy uses compact normalized relative completion-time states and job selection actions. • Theoretical analysis establishes consistency between the reward and objective. • DRLIPP improves solution quality by over 58% with consistent scalability.
Journal
IF:
8.5
Papers:
2.1K
Citations:
1.0W
Organization
Cited Papers