An Iterative Greedy Algorithm Involving a Q-Learning Mechanism for Solving the Permutation Flow Shop Scheduling Problem with Sequence-Dependent Setup Times
This paper proposes a novel hybrid framework, Q-IG, to solve the permutation flow shop scheduling problem with sequence-dependent setup times (PFSP-SDST). Recent advancements in learning-based methods demonstrate significant potential in addressing flow shop scheduling, yet they often struggle with the enormous solution space and the design of effective reward functions. To overcome these challenges, Q-IG integrates the iterated greedy metaheuristic (IG) with Q-learning. It begins by applying the Nawaz–Enscore–Ham (NEH) heuristic to generate high-quality initial solu