A Deep Reinforcement Learning (DRL)-Based Transformer Method for Solving the Open Shop Scheduling Problem
Researchers have developed a new method for solving the Open Shop Scheduling Problem (OSSP) using a Transformer-based deep reinforcement learning approach. This model, trained on smaller benchmark instances, demonstrates the ability to generalize to significantly larger problems without retraining. The Transformer-based policy offers a learning-based alternative to traditional dispatching rules, showing competitive performance against established heuristics like EST and outperforming SPT and LPT on large-scale instances. AI