文献类型：期刊文献

中文题名：强化学习原理、算法及应用

英文题名：Reinforcement Learning Theory,Algorithms and Application

作者：黄炳强[1];曹广益[1];王占全[2]

机构：[1]上海交通大学自动化系,上海200030;[2]华东理工大学计算机系,上海200237

年份：2006

卷号：35

期号：6

起止页码：34

中文期刊名：河北工业大学学报

外文期刊名：Journal of Hebei University of Technology

收录：CSTPCD

语种：中文

中文关键词：强化学习;TD算法;Q-学习;R-学习

外文关键词：reinforcement Learning; TD algorithm; Q-learning; R-learning

摘要：强化学习(ReinforcementLearningRL)是从动物学习理论发展而来的,它不需要有先验知识,通过不断与环境交互来获得知识,自主的进行动作选择,具有自主学习能力,在自主机器人行为学习中受到广泛重视.本文综述了强化学习的基本原理,各种算法,包括TD算法、Q-学习和R学习等,最后介绍了强化学习的应用及其在多机器人系统中的研究热点问题.
Reinforcement Learning develops from the animal learning theory. RL does not need prior knowledge, and it can autonomously improve its behavior policy with the knowledge obtained by continuously interacting with the environment. The main reinforcement learning algorithm including TD algorithm, Q-learning and R-learning are roundly introduced. Finally, the research and development on the multiple mobile robots system are presented.