強化学習における線形計画法を用いた効率的解法

• 泉田 啓

  京都大学大学院工学研究科

• 天野 恒佑

  京都大学大学院工学研究科

書誌事項

タイトル別名

• Efficient Algorithms for Reinforcement Learning by Linear Programming
• キョウカ ガクシュウ ニ オケル センケイ ケイカクホウ オ モチイタ コウリツテキカイホウ

抄録

Model-based reinforcement learning includes two steps, estimation of a plant and planning. Planning is formulated as dynamic programming (DP) problem, which is solved by a DP method. This DP problem has an equivalent linear programming (LP) problem that can be solved by LP method, but it is generally less efficient than typical DP method. However, numerical examples show linear programming is more efficient than the typical DP method in problems whose self-transition probabilities are large. The reason is clarified by geometrical discussion of each solution of method approaches to optimal solution.

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 52 (10), 566-572, 2016

  公益社団法人 計測自動制御学会

キーワード

• reinforcement learning
• planning
• linear programming
• self-transition probability

詳細情報

• CRID: 1390282679485390336
• NII論文ID: 130005432995
• NII書誌ID: AN00072392
• DOI: 10.9746/sicetr.52.566
• ISSN: 18838189
• ISSN: 04534654
• HANDLE: 2433/226829
• NDL書誌ID: 027720066
• Web Site: http://id.ndl.go.jp/bib/027720066
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I027720066
• Web Site: https://www.jstage.jst.go.jp/article/sicetr/52/10/52_566/_pdf
• 本文言語コード: ja
• データソース種別:
  • JaLC
  • IRDB
  • NDL
  • Crossref
  • CiNii Articles
  • KAKEN
• 抄録ライセンスフラグ: 使用不可