Simultaneous localization and mapping (SLAM) is a computational problem reconstructing the 3D environment map and estimating the camera trajectories simultaneously. This research topic has been studied for several decades in computer vision field. Among many other components in SLAM, we are concentrating on a loop closure detection determining whether a current view is visited by a camera agent before or not. It is an essential procedure for obtaining a consistent 3D environment map. In this paper, we propose a learning based local patch descriptor using a generative adversarial network to solve a problem of the loop closure detection. We trained the generative adversarial network on local patches of a place-oriented dataset and used the network model to extract the local patch descriptor. By using the descriptor on a general bag-of-visual-word method, we achieved better results than the conventional methods in terms of the precision and recall measure.