A study on use of prior information for acceleration of reinforcement learning

Kento Terashima, Junichi Murata

研究成果: 書籍/レポート タイプへの寄稿会議への寄与

5 被引用数 (Scopus)

抄録

Reinforcement learning is a method with which an agent learns appropriate response for solving problems by trial-and-error. The advantage is that reinforcement learning can be applied to unknown or uncertain problems. But instead, there is a drawback that this method needs a long time to solve the problem because of trial-and-error. If there is prior information about the environment, some of trial-and-error can be spared and the learning can take a shorter time. The prior information provided by a human designer can be wrong because of uncertainties in the problems. If the wrong prior information is used, there can be bad effects such as failure to get the optimal policy and slowing down of reinforcement learning. We propose to control use of the prior information to suppress the bad effects. The agent forgets the prior information gradually by multiplying a forgetting factor while it learns the better policy. We apply the proposed method to a couple of testbed environments and a number of types of prior information. The method shows the good results in terms of both the learning speed and the quality of obtained policies.

本文言語英語
ホスト出版物のタイトルSICE 2011 - SICE Annual Conference 2011, Final Program and Abstracts
出版社Society of Instrument and Control Engineers (SICE)
ページ537-543
ページ数7
ISBN(印刷版)9784907764395
出版ステータス出版済み - 1月 1 2011
イベント50th Annual Conference on Society of Instrument and Control Engineers, SICE 2011 - Tokyo, 日本
継続期間: 9月 13 20119月 18 2011

出版物シリーズ

名前Proceedings of the SICE Annual Conference

その他

その他50th Annual Conference on Society of Instrument and Control Engineers, SICE 2011
国/地域日本
CityTokyo
Period9/13/119/18/11

!!!All Science Journal Classification (ASJC) codes

  • 制御およびシステム工学
  • コンピュータ サイエンスの応用
  • 電子工学および電気工学

フィンガープリント

「A study on use of prior information for acceleration of 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