A learning algorithm for communicating Markov decision processes with unknown transition matrices

• 伊喜, 哲一郎

• 堀口, 正之

• 安田, 正實

• 蔵野, 正美

書誌事項

タイトル別名

• A learning algorithm for communicating Markov decision processes with unknown transition matrices(Mathematical Models and Decision Making under Uncertainty)
• learning algorithm for communicating Markov decision processes with unknown transition matrices

収録刊行物

• 数理解析研究所講究録

  数理解析研究所講究録 1477 127-135, 2006-03

  京都大学数理解析研究所

キーワード

• Adaptive policy
• communicating case
• average case
• reward-penalty type

詳細情報

• CRID: 1050282677273610752
• NII論文ID: 110004323502
• NII書誌ID: AN00061013
• ISSN: 18802818
• HANDLE: 2433/48242
• NDL書誌ID: 7936823
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I7936823
• 本文言語コード: en
• 資料種別: departmental bulletin paper
• データソース種別:
  • IRDB
  • NDL
  • CiNii Articles