Behavior Learning of Autonomous Robots by Modified Learning Vector Quantization

• Shon MIN KYU

  Graduate School of Information Science and Electrical Engineering, Kyushu University

• MURATA Junichi

  Graduate School of Information Science and Electrical Engineering, Kyushu University

• HIRASAWA Kotaro

  Graduate School of Information Science and Electrical Engineering, Kyushu University

抄録

This paper presents a method for searching for the optimal paths for autonomously moving agents in mazes by modified Learning Vector Quantization (LVQ) in a reinforcement learning framework. LVQ algorithm is faster than Q-learning algorithms because LVQ concentrates on the best behavior in available behaviors while Q-learning algorithms calculate values of all available behaviors and choose the best behavior among them. However, ordinary LVQ sometimes mis-learns in the reinforcement learning environment due to erroneous teacher signals. Here a new LVQ algorithm is proposed to overcome this problem, which finds the optimal path more efficiently.

収録刊行物

• 計測自動制御学会論文集

  計測自動制御学会論文集 37 (12), 1162-1168, 2001

  公益社団法人 計測自動制御学会

キーワード

• robot path finding
• Learning Vector Quantization (LVQ)
• reinforcement learning

詳細情報

• CRID: 1390001204501174784
• NII論文ID: 130003971000
• NII論文ID: 10007403499
• NII書誌ID: AN00072392
• DOI: 10.9746/sicetr1965.37.1162
• ISSN: 18838189
• ISSN: 04534654
• ISSN: http://id.crossref.org/issn/04534654
• NDL書誌ID: 6020343
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I6020343
• Web Site: https://www.jstage.jst.go.jp/article/sicetr1965/37/12/37_12_1162/_pdf
• 本文言語コード: en
• データソース種別:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
• 抄録ライセンスフラグ: 使用不可