文献类型：期刊文献

英文题名：Hierarchical reinforcement learning based on the clustering algorithm

作者：Zhu, Shanhong[1,2]

第一作者：朱珊虹;Zhu, Shanhong

通讯作者：Zhu, Shanhong

机构：[1] Xinxiang University, School of Computer and Information Engineering, Henan, China; [2] Wuhan University, International School of Software, Wuhan, China

第一机构：新乡学院计算机与信息工程学院

年份：2014

卷号：32

期号：5

起止页码：4503-4510

外文期刊名：Energy Education Science and Technology Part A: Energy Science and Research

收录：EI(收录号：20150700515854);Scopus(收录号：2-s2.0-84922463187)

语种：英文

外文关键词：Algorithms - Autonomous agents - Fuzzy clustering - Fuzzy sets - Learning algorithms - Reinforcement learning

摘要：In autonomous system, Agent assigns to their task through interaction with the environment, using hierarchical reinforcement learning technology can help the Agent in the large, complex environment to improve learning efficiency. A new method using fuzzy clustering algorithm identifies the layered boundary to find sub-goal condition, to automatic clustering of large state space, reaches the dimension reduction of state space, and on the basis of generated subspace clustering to structure subtasks, and then realizes the hierarchical learning tasks automatically. Through the experimental results the effectiveness of the proposed algorithm is demonstrated. ? Sila Science. All rights reserved.