Study on Q-learning algorithm based on ART2

Abstract

In order to solve the problem of dimension disaster, which may be produced by applying Q-learning to intelligent system of continuous state-space, we proposed a Q-learning algorithm based on ART2 in this paper, and give the specific steps. Through introducing the ART2 neural network in the Q-learning algorithm, Q-learning Agent in view of the duty which needs to complete to learn an appropriate incremental clustering of state-space model, so Agent can carry out decision-making and a two-tiers online learning of state-space model cluster in unknown environment, without any priori knowledge, through interaction with the environment unceasingly alternately to improve the control strategies, increase the learning accuracy. Finally through the mobile robot navigation simulation experiments, we show that, using the ARTQL algorithm, motion robot can improve its navigation performance continuously by interactive learning with the environment.