Good due date assignment for an order requires the calculation of a time bu
ffer that will account for the uncertainties associated with the arrival of
future orders in a dynamic environment. This paper presents a method that
controls the size of this time buffer for a discrete manufacturing system.
The applicability of the method to an unrestricted class of discrete manufa
cturing systems is preserved by the use of a feedback control paradigm, and
control knowledge is acquired using reinforcement learning. The current tr
ajectory of the state of the shop is considered so that due date performanc
e is improved during transient conditions. Results of simulation experiment
s demonstrate the effectiveness of the approach.