Reinforcement learning for problems with symmetrical restricted states

M. A.S. Kamal, Junichi Murata

研究成果: ジャーナルへの寄稿学術誌査読

8 被引用数 (Scopus)

抄録

A reinforcement learning method is proposed that can utilize parts of states and their partial symmetries to solve a problem efficiently. In most cases the action selection does not need considering all the states but only needs looking at parts of states or restricted state of corresponding action. Moreover, restricted states of different actions are symmetrical, and thus the action value function based on restricted states can be shared which further reduces the reinforcement learning problem size. The method is compared, in terms of simulation results and other aspects, with other standard reinforcement learning methods.

本文言語英語
ページ(範囲)717-727
ページ数11
ジャーナルRobotics and Autonomous Systems
56
9
DOI
出版ステータス出版済み - 9月 30 2008

!!!All Science Journal Classification (ASJC) codes

  • 制御およびシステム工学
  • ソフトウェア
  • 数学 (全般)
  • コンピュータ サイエンスの応用

フィンガープリント

「Reinforcement learning for problems with symmetrical restricted states」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