Enhanced continuous valued Q-learning for real autonomous robots

• TAKEDA Masanori

  Graduate School of Information Science, Nara Institute of Science and Technology

• NAKAMURA Takayuki

  Graduate School of Information Science, Nara Institute of Science and Technology

• IMAI Masakazu

  Graduate School of Information Science, Nara Institute of Science and Technology

• OGASAWARA Tsukasa

  Graduate School of Information Science, Nara Institute of Science and Technology

• ASADA Minoru

  Department of Adaptive Machine Systems, Osaka University

収録刊行物

• Advanced robotics : the international journal of the Robotics Society of Japan

  Advanced robotics : the international journal of the Robotics Society of Japan 14 (5), 439-441, 2000-06-01

キーワード

• Reinforcement learning
• weighted combination approach
• continuous valued Q-learning
• discontinuity problem of optimal actions

詳細情報

• CRID: 1570854174844151424
• NII論文ID: 10010911180
• NII書誌ID: AA10679021
• ISSN: 01691864
• 本文言語コード: en
• データソース種別:
  • CiNii Articles