Reinforcement learning for a biped robot based on a CPG-actor-critic method

• NAKAMURA Yutaka

  Nara Institute of Science and Technology

• MORI Takeshi

  Nara Institute of Science and Technology

• SATO Masa-aki

  ATR Computational Neuroscience Laboratories

• ISHII Shin

  Nara Institute of Science and Technology

収録刊行物

• Neural networks : the official journal of the International Neural Network Society

  Neural networks : the official journal of the International Neural Network Society 20 (6), 723-735, 2007-08-01

キーワード

• Reinforcement learning
• Central pattern generator
• Biped walking
• Actor-critic model
• Policy gradient method

詳細情報

• CRID: 1572261550349186176
• NII論文ID: 10019850710
• NII書誌ID: AA10680676
• ISSN: 08936080
• 本文言語コード: en
• データソース種別:
  • CiNii Articles