A Novel Clustering Method Curbing the Number of States in Reinforcement Learning
強化学習における状態数を抑制するクラスタリング方法

Naoki Kotani, Masayuki Nunobiki, Kenji Taniguchi
2009 Transactions of the Institute of Systems Control and Information Engineers  
We propose an efficient state-space construction method for a reinforcement learning. Our method controls the number of categories with improving the clustering method of Fuzzy ART which is an autonomous state-space construction method. The proposed method represents weight vector as the mean value of input vectors in order to curb the number of new categories and eliminates categories whose state values are low to curb the total number of categories. As the state value is updated, the size of
more » ... ategory becomes small to learn policy strictly. We verified the effectiveness of the proposed method with simulations of a reaching problem for a two-link robot arm. We confirmed that the number of categories was reduced and the agent achieved the complex task quickly. * 2008 2 25 †
doi:10.5687/iscie.22.21 fatcat:ngcg5jxvhnfv3egyyikg7jrezm