AI RESEARCH
RESCHED: Rethinking Flexible Job Shop Scheduling from a Transformer-based Architecture with Simplified States
arXiv CS.LG
•
ArXi:2603.07020v1 Announce Type: new Neural approaches to the Flexible Job Shop Scheduling Problem (FJSP), particularly those based on deep reinforcement learning (DRL), have gained growing attention in recent years. However, existing methods rely on complex feature-engineered state representations (i.e., often requiring than 20 handcrafted features) and graph-biased neural architectures. To reduce modeling complexity and advance a generalizable framework for FJSP, we