• DocumentCode
    2639744
  • Title

    Model-based reinforcement learning with model error and its application

  • Author

    Tajima, Yoshiyuki ; Onisawa, Takehisa

  • Author_Institution
    Univ. of Tsukuba, Tsukuba
  • fYear
    2007
  • fDate
    17-20 Sept. 2007
  • Firstpage
    1337
  • Lastpage
    1340
  • Abstract
    This paper proposes a reinforcement learning (RL) algorithm called model error based Forward planning reinforcement learning (ME-FPRL). In this algorithm, an agent controls the amount of learning by using the model error. This study applies ME-FPRL to the pursuit of a target by a robot camera. The results of this application show that ME-FPRL is more efficient than usual RL and model-based RL.
  • Keywords
    learning (artificial intelligence); legged locomotion; path planning; legged robot camera; model error based forward planning reinforcement learning; target task; Cameras; Dynamic programming; Electronic mail; Error correction; Humanoid robots; Humans; Intelligent robots; Laboratories; Learning; Robot vision systems; agent; model-based reinforcement learning; reinforcement learning; robot;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    SICE, 2007 Annual Conference
  • Conference_Location
    Takamatsu
  • Print_ISBN
    978-4-907764-27-2
  • Electronic_ISBN
    978-4-907764-27-2
  • Type

    conf

  • DOI
    10.1109/SICE.2007.4421190
  • Filename
    4421190
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2639744