Constructing continuous action space from basis functions for fast and stable reinforcement learning

Akihiko Yamaguchi, Jun Takamatsu, Tsukasa Ogasawara

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

This paper presents a new continuous action space for reinforcement learning (RL) with the wire-fitting [1]. The wire-fitting has a desirable feature to be used with action value function based RL algorithms. However, the wire-fitting becomes unstable caused by changing the parameters of actions. Furthermore, the acquired behavior highly depend on the initial values of the parameters. The proposed action space is expanded from the DCOB, proposed by Yamaguchi et al. [2], where the discrete action set is generated from given basis functions. Based on the DCOB, we apply some constraints to the parameters in order to obtain stability. Furthermore, we also describe a proper way to initialize the parameters. The simulation results demonstrate that the proposed method outperforms the wire-fitting. On the other hand, the resulting performance of the proposed method is the same as, or inferior to the DCOB. This paper also discuss about this result.

本文言語English
ホスト出版物のタイトルRO-MAN 2009 - 18th IEEE International Symposium on Robot and Human Interactive
ページ401-407
ページ数7
DOI
出版ステータスPublished - 2009 12 1
外部発表はい
イベント18th IEEE International Symposium on Robot and Human Interactive, RO-MAN 2009 - Toyama, Japan
継続期間: 2009 9 272009 10 2

出版物シリーズ

名前Proceedings - IEEE International Workshop on Robot and Human Interactive Communication

Other

Other18th IEEE International Symposium on Robot and Human Interactive, RO-MAN 2009
CountryJapan
CityToyama
Period09/9/2709/10/2

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Human-Computer Interaction

フィンガープリント 「Constructing continuous action space from basis functions for fast and stable 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