Volume 9 Number 3 (Mar. 2014)
Home > Archive > 2014 > Volume 9 Number 3 (Mar. 2014) >
JSW 2014 Vol.9(3): 634-640 ISSN: 1796-217X
doi: 10.4304/jsw.9.3.634-640

Statistics Based Q-learning Algorithm for Multi-Agent System and Application in RoboCup

Ya Xie, Zhonghua Huang
Hunan Institute of Engineering, Xiangtan, China

Abstract—This paper proposes statistic learning based Q-learning algorithm for Multi-Agent System, the agent can learn other agents’ action policies through observing and counting the joint action, a concise but useful hypothesis is adopted to denote the optimal policies of other agents, the full joint probability of policies distribution guarantees the optimal action choice to the learning agent. The algorithm can also improve the learning speed because the conventional Q-learning space is cut from exponential one to linear one. The convergence of the algorithm has been proved; the successful application of this algorithm in the RoboCup shows its good learning performance.

Index Terms—Q-learning, Statistics, Multi-agent, RoboCup


Cite: Ya Xie, Zhonghua Huang, "Statistics Based Q-learning Algorithm for Multi-Agent System and Application in RoboCup," Journal of Software vol. 9, no. 3, pp. 634-640, 2014.

General Information

ISSN: 1796-217X
Frequency: Monthly
Editor-in-Chief: Prof. Antanas Verikas
Executive Editor: Ms. Yoyo Y. Zhou
Abstracting/ Indexing: DBLP, EBSCO, ProQuest, INSPEC, ULRICH's Periodicals Directory, WorldCat, CNKI,etc
E-mail: jsw@iap.org
  • Nov 29, 2018 News!

    Papers published in JSW Vol. 13, No. 1- Vol. 13 No. 10 have been indexed by DBLP.    [Click]

  • Aug 24, 2018 News!

    Vol.12, No.8- Vol.13, No.5 has been indexed by EI (Inspec).   [Click]

  • Aug 01, 2018 News!

    [CFP] 2019 the annual meeting of JSW Editorial Board, ICCSM 2019, will be held in Barcelona, Spain, July 14-16, 2019.   [Click]

  • Nov 08, 2018 News!

    The papers published in Vol.13, No. 10 have all received dois from Crossref.

  • Nov 29, 2018 News!

    Vol 13, No. 12 has been published with online version 4 original aritcles from 3 countries are published in this issue.     [Click]