Reinforcement learning for high-dimensional problems with symmetrical actions

M. A.S. Kamal, Junichi Murata

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

5 被引用数 (Scopus)

抄録

A reinforcement learning algorithm is proposed that can cope with high dimensionality for a class of problems with symmetrical actions. The action selection does not need considering all the states but only needs looking at a part of the states. Moreover, every symmetrical action is related to the same kind of part of state, and thus the value function can be shared, which greatly reduces the reinforcement learning problem size. The overall learning algorithm is equivalent to the standard reinforcement learning algorithm. Simulation results and other aspects are compared with standard and other reinforcement learning algorithms. Reduction in dimensionality, much faster convergence without worsening other objectives show the effectiveness of the proposed mechanism on a high dimensional optimization problem having symmetrical actions.

本文言語英語
ホスト出版物のタイトル2004 IEEE International Conference on Systems, Man and Cybernetics, SMC 2004
ページ6192-6197
ページ数6
DOI
出版ステータス出版済み - 12 1 2004
イベント2004 IEEE International Conference on Systems, Man and Cybernetics, SMC 2004 - The Hague, オランダ
継続期間: 10 10 200410 13 2004

出版物シリーズ

名前Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
7
ISSN(印刷版)1062-922X

その他

その他2004 IEEE International Conference on Systems, Man and Cybernetics, SMC 2004
国/地域オランダ
CityThe Hague
Period10/10/0410/13/04

All Science Journal Classification (ASJC) codes

  • 工学(全般)

フィンガープリント

「Reinforcement learning for high-dimensional problems with symmetrical actions」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル