In this study, we consider different MDPs for items in an assembly line. In other words, each item's production is associated with a distinct MDP. In each decision stage for each model, the system is in a state, and an action is selected from the actions set associated with that state. The probability of switching from a state to another with an action is calculated. The most common methods for finding the optimal policies for MDPs are the linear programming method, the policy iteration algorithm, and the value iteration algorithm. In comparison to other approaches, linear programming is rarely used to solve MDPs. However, the LP solution methods are efficient and flexible enough to accommodate various constraints that links the different MDPs.