Introduction and control of subgoals in reinforcement learning

Junichi Murata, Yasuomi Abe, Keisuke Ota

研究成果: 書籍/レポート タイプへの寄稿会議への寄与

1 被引用数 (Scopus)

抄録

Reinforcement learning (RL) can be applied to a wide class of problems because it requires no other information than perceived states and rewards to find good action policies. However, it takes a large number of trials before acquiring the optimal policy. In order to make RL faster, use of subgoals is proposed. Since errors and ambiguity are inevitable in subgoal information provided by human designers, a mechanism is proposed that controls use of subgoals. The method is applied to examples and the results show that use of subgoals is very effective in accelerating RL and that the proposed control mechanism successfully suppresses possible critical damages on the RL performance caused by errors and ambiguity in subgoal information.

本文言語英語
ホスト出版物のタイトルProceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2007
ページ329-334
ページ数6
出版ステータス出版済み - 12月 1 2007
イベントIASTED International Conference on Artificial Intelligence and Applications, AIA 2007 - Innsbruck, オーストリア
継続期間: 2月 12 20072月 14 2007

出版物シリーズ

名前Proceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2007

その他

その他IASTED International Conference on Artificial Intelligence and Applications, AIA 2007
国/地域オーストリア
CityInnsbruck
Period2/12/072/14/07

!!!All Science Journal Classification (ASJC) codes

  • 人工知能
  • コンピュータ サイエンスの応用

フィンガープリント

「Introduction and control of subgoals in reinforcement learning」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル