A policy representation using weighted multiple normal distribution real-time reinforcement learning feasible for varying optimal actions

Hajime Kimura, Takeshi Aramaki, Shigenobu Kobayashi

研究成果: Contribution to journalArticle査読

3 被引用数 (Scopus)

抄録

In this paper, we challenge to solve a reinforcement learning problem for a 5-linked ring robot within a real-time so that the real-robot can stand up to the trial and error. On this robot, incomplete perception problems are caused from noisy sensors and cheap position-control motor systems. This incomplete perception also causes varying optimum actions with the progress of the learning. To cope with this problem, we adopt an actor-critic method, and we propose a new hierarchical policy representation scheme, that consists of discrete action selection on the top level and continuous action selection on the low level of the hierarchy. The proposed hierarchical scheme accelerates learning on continuous action space, and it can pursue the optimum actions varying with the progress of learning on our robotics problem. This paper compares and discusses several learning algorithms through simulations, and demonstrates the proposed method showing application for the real robot.

本文言語英語
ページ(範囲)316-324
ページ数9
ジャーナルTransactions of the Japanese Society for Artificial Intelligence
18
6
DOI
出版ステータス出版済み - 2003
外部発表はい

All Science Journal Classification (ASJC) codes

  • ソフトウェア
  • 人工知能

フィンガープリント

「A policy representation using weighted multiple normal distribution real-time reinforcement learning feasible for varying optimal 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