Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Computer Engineering and Applications》 2009-34
Add to Favorite Get Latest Update

Parallel reinforcement learning algorithm and its application

MENG Wei,HAN Xue-dong.1.Information School,Beijing Forestry University,Beijing 100083,China 2.706 Institute of China Aerospace Science and Industry Corporation,Beijing 100854,China  
Reinforcement learning is an important machine learning method.However,slow convergence has been one of main problem in practice.To improve the efficiency of reinforcement learning,this paper proposes parallel reinforcement learning algo-rithm.There are multiple agents in learning system.In a learning episode,each agent learns independently.After a learning episode,the results of all agents are fused based on D-S evidence theory so as to achieve common result,which are shared by all agents in next learning episode.Experiments show the feasibility and efficiency of the algorithm.
【Fund】: 国家“十一五”科技支撑计划重大项目资助No.2006BAD03A02~~
【CateGory Index】: TP18
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
【Citations】
Chinese Journal Full-text Database 5 Hits
1 TONG-liang,LU Ji-lian,GONG Jian-wei(School of Mechanical and Vehicular Engineering, Beijing Institute of Technology, Beijing100081, China);Research on Fast Reinforcement Learning[J];Journal of Beijing Institute of Technology;2005-04
2 Zhang Rubo(Dept.of Computer Science,Harbin Engineering University,Harbin150001);Research on the Method to Improve Reinforcement Learning Speed[J];Computer Engineering and Applications;2001-22
3 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
4 ZHONG Yu, GU Guo-chang, ZHANG Ru-bo (1.Computer Science and Technology College,Harbin Engineering University,Heilongjiang Harbin 150001,China; (2.Robotics Laboratory,Shenyang Institute of Automation,Chinese Academy of Sciences,Liaoning Shenyang 110015,China);Survey of distributed reinforcement learning algorithms in multi-agent systems[J];Control Theory & Applications;2003-03
5 CHU Hai-tao, HONG Bing-rong (Department of Computer Science and Engineering, Harbin Institute of Technology, Harbin 150001, China);Multi Robots Cooperative Based on Action Selection Level[J];Journal of Software;2002-09
【Secondary Citations】
Chinese Journal Full-text Database 7 Hits
1 Zhao Li Dong Hongbin(Harbin Normal University);APPLICATION ON MULTI-AGENT SYSTEM IN THE ROBOT WORLD CUP[J];Natural Science Journal of Harbin Normal University;2005-02
2 GAO Yang; ZHOU Zhi-Hua; HE Jia-Zhou; CHEN Shi-Fu (State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210093);RESEARCH ON MARKOV GAME-BASED MULTIAGENT REINFORCEMENT LEARNING MODEL AND ALGORITHMS[J];JOURNAL OF COMPUTER RESEARCH AND DEVELOPMENT;2000-03
3 CAI Qing Sheng and ZHANG Bo (Department of Computer Science and Technology, University of Science and Technology of China, Hefei 230027);AN AGENT TEAM BASED REINFORCEMENT LEARNING MODEL AND ITS APPLICATION[J];JOURNAL OF COMPUTER RESEARCH AND DEVELOPMENT;2000-09
4 LI Nan,LIU Guo-dong(Control Science and Engineering Research Center,Southern Yangtze University,Wuxi Jiangsu 214122,China);Intrinsic Motivation Reinforcement Learning and Its Application to Robocup Simulation[J];Computer Simulation;2006-04
5 ZHANG Rubo, GU Guochang, LIU Zhaode\ and WANG Xingce (Department of computer science,Harbin Engineering University·Harbin,150001,P.R.China);Reinforcement Learning Theory,Algorithms and Its Application[J];CONTROL THEORY & APPLICATIONS;2000-05
6 DU Chunxia, GAO Yun, ZHANG Wen(Department of Computer Science, Ocean University of China, Qingdao 266071, China);Q-learning with prior knowledge in multi-agent systems[J];Journal of Tsinghua University(Science and Technology);2005-07
7 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
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved