R-learning with multiple state-action value tables

Koichiro Ishikawa, Akito Sakurai, Tsutomu Fujinami, Susumu Kunifuji

研究成果: Article査読

抄録

We propose a method to improve the performance of R-learning, a reinforcement learning algorithm, by using multiple state-action value tables. Unlike Q- or Sarsa learning, R-learning learns a policy to maximize undiscounted rewards. Multiple state-action value tables cause substantial explorations as needed and make R-learnings to work well. Efficiency of the proposed method is verified through experiments in simulation environment.

本文言語English
ページ(範囲)72-82
ページ数11
ジャーナルIEEJ Transactions on Electronics, Information and Systems
126
1
DOI
出版ステータスPublished - 2006

ASJC Scopus subject areas

  • 電子工学および電気工学

フィンガープリント

「R-learning with multiple state-action value tables」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