実ロボットによる行動学習のための状態空間の漸次的構成 Incremental State Space Segmentation for Behavior Learning by Real Robot

この論文にアクセスする

この論文をさがす

著者

抄録

Reinforcement learning has recently been receiving increased attention as a method for robot learning with little or no <i>a priori</i> knowledge and higher capability of reactive and adaptive behaviors. However, there are two major problems in applying it to real robot tasks: how to construct the state space, and how to accelerate the learning. This paper presents a method by which a robot learns a purposive behavior within less learning time by incrementally segmenting the sensor space based on the experiences of the robot. The incremental segmentation is performed by constructing local models in the state space, which is based on the function approximation in terms of the sensor outputs and the reinforcement signal to reduce the learning time. The method is applied to a soccer robot which tries to shoot a ball into a goal. The experiments with computer simulations and a real robot are shown. As a result, our real robot has learned a shooting behavior within less than one hour training by incrementally segmenting the state space.

収録刊行物

  • 日本ロボット学会誌  

    日本ロボット学会誌 17(1), pp.118-124, 1999-01-15 

    The Robotics Society of Japan

参考文献:  15件

参考文献を見るにはログインが必要です。ユーザIDをお持ちでない方は新規登録してください。

被引用文献:  30件

被引用文献を見るにはログインが必要です。ユーザIDをお持ちでない方は新規登録してください。

各種コード

  • NII論文ID(NAID)
    10002865456
  • NII書誌ID(NCID)
    AN00141189
  • 本文言語コード
    JPN
  • 資料種別
    ART
  • ISSN
    02891824
  • NDL 記事登録ID
    3087138
  • NDL 雑誌分類
    ZN11(科学技術--機械工学・工業)
  • NDL 請求記号
    Z16-1325
  • データ提供元
    CJP書誌  CJP引用  NDL  J-STAGE 
ページトップへ