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 Online Bahavior Aquisition of an Agent based on Coaching as Learning Assistance

この論文にアクセスする

著者

    • 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

抄録

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.

収録刊行物

  • 人工知能学会論文誌

    人工知能学会論文誌 25(6), 694-702, 2010

    一般社団法人 人工知能学会

各種コード

  • NII論文ID(NAID)
    130000341879
  • 本文言語コード
    JPN
  • データ提供元
    J-STAGE 
ページトップへ