抄録
One of the reinforcement learning algorithms proposed by Igarashi and Ishihara is a combining method of policy gradient method and fuzzy control. In 2012, M. Sugimoto implemented the algorithm to the RoboCup Small Size League action decision system. The system received 30 scenes, taken from RoboCup Japan Open 2012 Competition to be learned. The purpose of this paper is to present the detailed analysis on the fuzzy rules in the policies taken from the system in order to find out the cause of the failure in the learning of 5 of the scenes received. A method was proposed to determine the rules that caused error in the learning of 5 scenes by evaluating the degree of contribution and divergence of each rule.
本文言語 | English |
---|---|
ホスト出版物のタイトル | International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2014, Held at the 3rd World Congress on Computing and Information Technology, WCIT |
出版社 | Society of Digital Information and Wireless Communications (SDIWC) |
ページ | 167-174 |
ページ数 | 8 |
出版ステータス | Published - 2014 |
イベント | International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2014 - Kuala Lumpur, Malaysia 継続期間: 2014 11月 17 → 2014 11月 19 |
Other
Other | International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2014 |
---|---|
国/地域 | Malaysia |
City | Kuala Lumpur |
Period | 14/11/17 → 14/11/19 |
ASJC Scopus subject areas
- 人工知能
- コンピュータ ビジョンおよびパターン認識