• ISSN 0258-2724
  • CN 51-1277/U
  • EI Compendex
  • Scopus
  • Indexed by Core Journals of China, Chinese S&T Journal Citation Reports
  • Chinese S&T Journal Citation Reports
  • Chinese Science Citation Database
Volume 22 Issue 6
Mar.  2010
Turn off MathJax
Article Contents
SHEN Yuanxia, WANG Guoyin. Data-Driven Q-Learning in Dynamic Environment[J]. Journal of Southwest Jiaotong University, 2009, 22(6): 877-881.
Citation: SHEN Yuanxia, WANG Guoyin. Data-Driven Q-Learning in Dynamic Environment[J]. Journal of Southwest Jiaotong University, 2009, 22(6): 877-881.

Data-Driven Q-Learning in Dynamic Environment

  • Received Date: 27 Jun 2008
  • Publish Date: 20 Jan 2010
  • It is difficult for reinforcement learning to balance between the exploration of untested actions and the exploitation of known optimum actions in dynamic environment.To address this problem,a data-driven Q-learning algorithm was proposed.In this algorithm,the information system of behavior is constructed for each agent.Then the trigger mechanism of environment is build by the uncertainty of knowledge in the information system of behavior to trace the environmental change.The dynamic information of the environment is used to exploit new environment by the trigger mechanism to achieve the balance between the exploration of untested actions and the exploitation of know optimum actions.The proposed algorithm was applied to grid-world navigation tasks.The simulation results show that compared with the Q-learning,simulated annealing Q-learning(SAQ) and recency-based exploration(RBE) Q-learning algorithms,the proposed algorithm has a high learning efficiency.

     

  • loading
  • 高阳,陈世福,陆鑫.强化学习研究综述[J].自动化学报,2004,30(1):86-100.GAO Yang,CHEN Shifu,LU Xin.Research on reinforcement learning technology:a review[J].Acta Automatica Sinica,2004,30(1):86-100.[2] SUITON R S,BARTO S.Reinforcement learning[M].Cambridge:MIT Press,1998.[3] ZHANG Kaifu,PAN Wei.The two facets of the exploration-exploitation dilemma[C]//Proceedings of the IEEE/WIC/ACM International Conference on Intelligent Agent Technology.Hongkong:IEEE Press,2006:371-380[4] ZHU S,DANA D H.Overcoming non-stationary in uncommunicative learning[D].New Brunswick:Rutgers University,2002.[5] WIERING M A,SCHMIDHUBER J.Efficient model based exploration[C]// Proceedings of the Fifth International Conference on Simulation of Adaptive Behavior.Zurich:MIT Press,1998:223-228.[6] KABLBLING I P,LITTMAN M L,MOORE A W.Reinforcement learning:A survey[J].J Artificial Intelligence Research,1996,4:237-285.[7] PETERS J F,HENRY C.Approximation spaces in off-policy monte carlo learning[J].Engineering Applications of Artificial Intelligence,2007,20(5):667-675.[8] VIEN N A,VIET N H,LEE S G.Heuristic search based exploration in reinforcement learning[C]//Computational and Ambient Intelligence,9th International Work-Conference on Artificial Neural Networks.Heidelberg:Springer-Verlag,4507:110-118.[9] GUO Maozu,LIU Yang,MALEC J.A new Q-learning algorithm based on the metropolis criterion[J].IEEE Transactions on Systems,Man,and Cybernetics,2004,5(34):2140-2143.[10] WANG Guoyin.Domain-oriented data-driven data mining (3DM):simulation of human knowledge understanding[C]//Web Intelligence Meets Brain Informatics.Heidelberg:Springer-Verlag,2007,4845:278-290.
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索
    Article views(1590) PDF downloads(341) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return