| 强化学习原理、算法及应用 |
| |
| 引用本文： | 黄炳强,曹广益,王占全.强化学习原理、算法及应用[J].河北工业大学学报,2006,35(6):34-38. |
| |
| 作者姓名： | 黄炳强 曹广益 王占全 |
| |
| 作者单位： | 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 |
| |
| 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.
|
| 关 键 词： | 强化学习 TD算法 Q-学习 R-学习 |
| 文章编号： | 1007-2373(2006)06-0034-05 |
| 修稿时间： | 2006年8月5日 |
Reinforcement Learning Theory, Algorithms and Application |
| |
| HUANG Bing-qiang,CAO Guang-yi,WANG Zhan-quan.Reinforcement Learning Theory, Algorithms and Application[J].Journal of Hebei University of Technology,2006,35(6):34-38. |
| |
| Authors: | HUANG Bing-qiang CAO Guang-yi WANG Zhan-quan |
| |
| Abstract: | 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 envi- ronment. The main reinforcement learning algorithm including TD algorithm, Q-learning and R-learning are roundly in- troduced. Finally, the research and development on the multiple mobile robots system are presented. |
| |
| Keywords: | reinforcement Learning TD algorithm Q-learning R-learning |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
