Using reinforcement learning to select an optimal feature set

Feature Selection (FS) is an essential research topic in the area of machine learning. FS, which is the process of identifying the relevant features and removing the irrelevant and redundant ones, is meant to deal with the high dimensionality problem for the sake of selecting the best performing feature subset. In the literature, many feature selection techniques approach the task as a research problem, where each state in the search space is a possible feature subset. In this paper, we introduce a new feature selection method based on reinforcement learning. First, decision tree branches are used to traverse the search space. Second, a transition similarity measure is proposed so as to ensure exploit-explore trade-off. Finally, the informative features are the most involved ones in constructing the best branches. The performance of the proposed approaches is evaluated on nine standard benchmark datasets. The results using the AUC score show the effectiveness of the proposed system.