Natural gradient actor-critic algorithms using random rectangular coarse coding

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

2 被引用数 (Scopus)

抄録

Learning performance of natural gradient actor-critic algorithms is outstanding especially in high-dimensional spaces than conventional actor-critic algorithms. However, representation issues of stochastic policies or value functions are remaining because the actor-critic approaches need to design it carefully. The author has proposed random rectangular coarse coding, that is very simple and suited for approximating Q-values in high-dimensional state-action space. This paper shows a quantitative analysis of the random coarse coding comparing with regular-grid approaches, and presents a new approach that combines the natural gradient actor-critic with the random rectangular coarse coding.

本文言語英語
ホスト出版物のタイトルProceedings of SICE Annual Conference 2008 - International Conference on Instrumentation, Control and Information Technology
ページ2027-2034
ページ数8
DOI
出版ステータス出版済み - 12 1 2008
イベントSICE Annual Conference 2008 - International Conference on Instrumentation, Control and Information Technology - Tokyo, 日本
継続期間: 8 20 20088 22 2008

出版物シリーズ

名前Proceedings of the SICE Annual Conference

その他

その他SICE Annual Conference 2008 - International Conference on Instrumentation, Control and Information Technology
Country日本
CityTokyo
Period8/20/088/22/08

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

フィンガープリント 「Natural gradient actor-critic algorithms using random rectangular coarse coding」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