A Q-Learning for Group-Based Plan of Container Transfer Scheduling

Abstract

In container yard terminals, containers brought by trucks arrive in the random order. Since each container has its own destination and it cannot be rearranged after shipping, containers have to be loaded into a ship in a certain order. Therefore, containers have to be rearranged from the initial arrangement into the desired arrangement before shipping. In the problem, the number of container-arrangements increases by the exponential rate with increase of total count of containers. Therefore, conventional methods have great difficulties to determine desirable movements of containers in order to reduce the run time for shipping. In this paper, a Q-Learning algorithm based on the number of container-movements for the material handling in the container yard terminal is proposed. In the proposed method, each container has several desired positions, so that the learning performance can be improved. In order to show effectiveness of the proposed method, simulations for several examples are conducted.