Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Computer Engineering and Applications》 2001-22
Add to Favorite Get Latest Update

Research on the Method to Improve Reinforcement Learning Speed

Zhang Rubo(Dept.of Computer Science,Harbin Engineering University,Harbin150001)  
The word,reinforcement learning,comes from behavior psychology.This subject takes learning as trial and er-ror process so as to map world state to the actions.This characteristic of reinforcement learning must increase learning difficulty for intelligent system and learning time also grows up.The reason of lower learning speed for reinforcement learning is due to that explicit supervised signal doesn't exist.Therefore reinforcement learning agent has to take trial and error method when interaction with environment and adjusts its behavior by external critic.The agent must experi-ence a long learning process.Thus how reinforcement learning speed is improved is a crucial problem.In this paper,the methods that improve reinforcement learning speed are discussed in many aspects.
【Fund】: 黑龙江省自然科学基金F9911;; 国防基础计划项目的资助
【CateGory Index】: TP18
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
【References】
Chinese Journal Full-text Database 3 Hits
1 ZHANG Yun,LIU Jian-ping(College of Mechatronical Engineering&Automation of National University of Defense Technology,Changsha Hunan 410073,China);Research on Improvement of Q-Learning and Its Simulation Experiments[J];Computer Simulation;2007-10
2 ZHAN Zhong-li1,WANG Qiang1,WANG Peixia2 (1.Jilin Technology University of Electric Information,Jilin 132012,China 2.Liaoning Agricultural College,Yingkou,115009,China);Q-Learning in Multi-Agent Systems[J];Journal of Liaoning Agricultural College;2008-05
3 SONG Qing-kun,HU Zi-ying(Automation,Harbin Univ.Sci.Tech.,Harbin 150080,China);Q-Learning based on the Experience knowledge[J];Techniques of Automation and Applications;2006-11
【Co-references】
Chinese Journal Full-text Database 10 Hits
1 Duan Qunjie,Zhang Mingjun and Others;Local Path Planning Method for AUV Based on Fuzzy-neural Network[J];Ship Engineering;2001-01
2 Wang Long Zhang Yi Wu Yue (School of Computer Science and Engineering, UEST of China Chengdu 610054);Key Techniques to Realize Cooperation of Mobile Agent in MAS Environment[J];Journal of University of Electronic Science and Technology of China;2003-02
3 ;Summary of Collaborative Filtering[J];Computer Development & Applications;2002-11
4 PANG Su-chao, CHEN Shi(Management Department, Mudanjiang University, Mudanjiang, Heilongjiang 157011, China );Solution to shortest path with dynamic programming[J];Journal of Daqing Petroleum Institute;2007-03
5 LIU Xiaosheng WU Lenan Radio Department, South East University (210018);Thinking about the Development of Intelligent Residential Quarters in Our Country[J];LOW VOLTAGE APPARATUS;2000-01
6 LIN Jin-xian 1, ZHONG Chun-fang 2 (1. Centre of Network, Fuzhou University, Fuzhou Fujian 350002, China; 2.Department of Computer Science and Technology, Fuzhou University, Fuzhou Fujian 350002, China);Agent-Based Self-Adaptive Web Information Search Model[J];JOURNAL OF FUZHOU UNIVERSITY(NATURAL SCIENCES EDTION);2000-03
7 LI Wen yong, LI Quan yong (Dept. of Electronic Machinery and Traffic Engineering,Guilin 541004,China);The Global Optimization Algorithm Based on Simulated Annealing[J];Journal of Guilin Institute of Electronic Technology;2001-02
8 HUANG Bing-qiang1,CAO Guang-yi1,WANG Zhan-quan2 ( 1. Department of Automation, Shanghai Jiaotong University, Shanghai 200030, China; 2. Department of Computer Science, East China University of Science and Technology, Shanghai 200237, China );Reinforcement Learning Theory,Algorithms and Application[J];Journal of Hebei University of Technology;2006-06
9 WANG Xingce,ZHANG Rubo,GU Guochang (School of Computer Science and Technology , Harbin Engineering University , Harbin 150001,China);Potential grid based global path planning for robots[J];Journal of Harbin Engineering University;2003-02
10 LU Jun~1, XU Li~2,ZHOU Xiao-ping~2 (1. School of Automation, Harbin Engineering University, Harbin 150001,China;2. China Ordnance Test Center of Baicheng, Baicheng 137001, China);Research on reinforcement learning and its application to mobile robot[J];Journal of Harbin Engineering University;2004-02
【Secondary References】
Chinese Journal Full-text Database 3 Hits
1 MAO Jun-jie,LIU Guo-dong School of Communications and Control Engineering,Jiangnan University,Wuxi,Jiangsu 214122,China;Modified reinforcement learning based on experience konwledge and its application in MAS[J];Computer Engineering and Applications;2008-24
2 MENG Xiang-ping1,WANG Sheng-bin2,WANG Xin-xin2 1.Department of Electrical Engineering,Changchun Institute of Technology,Changchun 130012,China 2.Department of Computer Engineering,Northeast Dianli University,Jilin 132012,China;Multiagent Q-learning based on ant colony algorithm and roulette algorithm[J];Computer Engineering and Applications;2009-16
3 MENG Xiang-ping1,WANG Sheng-bin2,WANG Xin-xin2(1.Department of Electrical Engineering,Changchun Institute of Technology,Changchun 130012,China;2.Department of Computer Engineering,Northeast Dianli University,Jilin 132012,China);Study for some problems of multi-agent Q-learning and improving[J];Computer Engineering and Design;2009-09
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved