Automated material handling systems (AMHS) are essential for industrial semiconductor production in modern front-end facilities. The control of these systems has a significant impact on ensuring a reliable supply of production resources. Allocating transportation tasks to vehicles in real time is of great importance here, as it represents a computational challenge and has a major impact on the performance of the transportation system (see Wu et al., 2019). Achieving the best possible operation is the subject of numerous research activities (see De Ryck et al., 2020).

Machine learning approaches enable new ways of developing control strategies to achieve higher system performance (see Bai et al., 2023). Our paper provides two examples of how machine learning can be applied to improve task assignment for empty vehicles.