教示者による学習支援に基づくエージェントのオンライン行動獲得  [in Japanese] Online Bahavior Aquisition of an Agent based on Coaching as Learning Assistance  [in Japanese]

Access this Article

Author(s)

    • 廣川 暢一 HIROKAWA Masakazu
    • 筑波大学大学院システム情報工学研究科 Graduate School of Intelligence Interaction Technologies, University of Tsukuba
    • 鈴木 健嗣 SUZUKI Kenji
    • 筑波大学大学院システム情報工学研究科 Graduate School of Intelligence Interaction Technologies, University of Tsukuba

Abstract

This paper describes a novel methodology, namely ``Coaching'', which allows humans to give a subjective evaluation to an agent in an iterative manner. This is an interactive learning method to improve the reinforcement learning by modifying a reward function dynamically according to given evaluations by a trainer and the learning situation of the agent. We demonstrate that the agent can learn different reward functions by given instructions such as ``good or bad'' by human's observation, and can also obtain a set of behavior based on the learnt reward functions through several experiments.

Journal

  • Transactions of the Japanese Society for Artificial Intelligence

    Transactions of the Japanese Society for Artificial Intelligence 25(6), 694-702, 2010

    The Japanese Society for Artificial Intelligence

Codes

  • NII Article ID (NAID)
    130000341879
  • Text Lang
    JPN
  • ISSN
    1346-0714
  • Data Source
    J-STAGE 
Page Top