Search this article in Google Scholar


分類 論文誌
著者名 (author) Hiroshi Osada,Satoshi Fujita
英文著者名 (author)
キー (key)
表題 (title) {CHQ}: A Multiagent Reinforcement Learning Scheme for Partially Observable Markov Decision Processes
表題 (英文)
定期刊行物名 (journal) IEICE Trans. Information and Systems
定期刊行物名 (英文)
巻数 (volume) E88-D
号数 (number) 5
ページ範囲 (pages) 1004-1011
刊行月 (month) May
出版年 (year) 2005
付加情報 (note)
注釈 (annote)
内容梗概 (abstract) In this paper, we propose a new reinforcement learning scheme called CHQ that could efficiently acquire appropriate policies under partially observable Markov decision processes (POMDP) involving probabilistic state transitions, that frequently occurs in multi-agent systems in which each agent independently takes a probabilistic action based on a partial observation of the underlying environment. A key idea of CHQ is to extend the HQ-learning proposed by Wiering et al. in such a way that it could learn the activation order of the MDP subtasks as well as an appropriate policy under each MDP subtask. The goodness of the proposed scheme is experimentally evaluated. The result of experiments implies that it can acquire a deterministic policy with a sufficiently high success rate, even if the given task is POMDP with probabilistic state transitions.
論文電子ファイル Not available.


[0-13]  Hiroshi Osada and Satoshi Fujita, ``CHQ: a Multiagent Reinforcement Learning Scheme for Partially Observable Markov Decision Processes,'' IEICE Trans. Information and Systems, vol. E88-D, no. 5, pp. 1004-1011 , May 2005.

@article{0_13,
    author = {Hiroshi Osada and Satoshi Fujita},
    author_e = {},
    title = {{CHQ}: A Multiagent Reinforcement Learning Scheme for Partially
    Observable Markov Decision Processes},
    title_e = {},
    journal = {IEICE Trans. Information and Systems},
    journal_e = {},
    volume = {E88-D},
    number = {5},
    pages = {1004-1011 },
    month = {May},
    year = {2005},
    note = {},
    annote = {}
}

This site is maintained by Distributed System Laboratory.

PMAN 2.5.5 - Paper MANagement system / (C) 2002-2008, Osamu Mizuno / All rights reserved.