遺伝的プログラミングと強化学習の統合に基づく実ロボットの行動獲得  [in Japanese] Integration of Genetic Programming and Reinforcement Learning for Real Robots  [in Japanese]

Access this Article

Search this Article

Author(s)

Abstract

本論文では,遺伝的プログラミングと強化学習を統合した,実ロボットでの実時間学習が可能な手法を提案する.提案手法では,高精度のシミュレータは必要としない.なぜなら学習はシミュレータ上だけではなく,実ロボット上でも行われるからである.このため実ロボットでの最適行動を得ることができる.本論文では提案手法に基づき実ロボットAIBOで行った実験結果を示し,提案手法が従来のQ学習手法よりも性能が良いことを示す.We propose an integrated technique of genetic programming (GP) and reinforcement learning (RL) that allows a real robot to execute real-time learning. Our technique does not need a precise simulator because learning is done with a real robot. Moreover, our technique makes it possible to learn optimal actions in real robots. We show the result of an experiment with a real robot AIBO and represents the result which proves proposed technique performs better than traditional Q-learning method.

We propose an integrated technique of genetic programming (GP) and reinforcement learning (RL) that allows a real robot to execute real-time learning. Our technique does not need a precise simulator because learning is done with a real robot. Moreover, our technique makes it possible to learn optimal actions in real robots. We show the result of an experiment with a real robot AIBO and represents the result which proves proposed technique performs better than traditional Q-learning method.

Journal

  • 情報処理学会論文誌数理モデル化と応用(TOM)

    情報処理学会論文誌数理モデル化と応用(TOM) 45(SIG02(TOM10)), 134-143, 2004-02-15

    Information Processing Society of Japan (IPSJ)

References:  13

Codes

  • NII Article ID (NAID)
    110002712331
  • NII NACSIS-CAT ID (NCID)
    AA11464803
  • Text Lang
    JPN
  • Article Type
    Article
  • ISSN
    1882-7780
  • NDL Article ID
    6851087
  • NDL Call No.
    Z74-C192
  • Data Source
    CJP  NDL  NII-ELS  IPSJ 
Page Top