A multiobjective flexible job shop scheduling method based on deep reinforcement learning

To address the multiobjective flexible job shop scheduling problem, this paper establishes a Markov Decision Process for Multiobjective Flexible Job-Shop Scheduling Problem, aiming to minimize makespan and total machine load. Additionally, a multiobjective optimization algorithm base deep reinforcement learning is proposed. Firstly, a multiobjective decomposition strategy is introduced to decompose the problem into a set of subproblems, and graph neural networks with identical structures are employed to represent the priority dispatching rules for each subproblem. Experimental results demonstrate that this approach exhibits better generalization, higher solution quality, and faster convergence compared to previous methods.