Job shop scheduling is a key technology in modern manufacturing. Scheduling performance will decide the enterprises’ core competitiveness. In this paper, improved reinforcement learning with cohesion is used in dynamic job shop environment, and it eased the contradiction of precocious and slow convergence. Also the machine choice is considered. So the dual scheduling which included job and machine is achieved in this system. And it obtains better results through the experiments. The utilization of equipments and the emergency handling capacity can be improved in the dynamic environment.
An improved deep reinforcement learning approach for the dynamic job shop scheduling problem with random job arrivals
