This thesis concentrates on a subfield of AI, the field of Learning Automata (LA). We intend to use these tools to tackle a specific set of problems referred to as Elevator-Like Problems. We considered a problem that involves the problem of optimizing the scheduling of elevators. In particular, we are concerned with determining the Elevators' optimal ``parking" locations. Problems with similar characteristics are referred to as Elevator-like Problems. In our case, the objective is to find the optimal parking floors for the set of elevators to minimize the passengers' Average Waiting Time. We provided two novel LA-based solutions for two settings, the single-elevator and the multi-elevator. The first pair are L_RI-based solutions, and the second pair incorporate the Pursuit concept to improve the performance, yielding the PL_RI-based solutions. The results demonstrate that our solutions performed better than those used in modern-day elevators, with near-optimal results, and up-to 90% performance increase.