Learning of Soccer player agents using a policy gradient method: Pass selection

Harukazu Igarashi, Hitoshi Fukuoka, Seiji Ishihara

研究成果

1 被引用数 (Scopus)

抄録

This research develops a learning method for the pass selection problem of midfielders in RoboCup Soccer Simulation games. A policy gradient method is applied as a learning method to solve this problem because it can easily represent the various heuristics of pass selection in a policy function. We implement the learning function in the midfielders' programs of a well-known team, UvA Trilearn Base 2003. Experimental results show that our method effectively achieves clever pass selection by midfielders in full games. Moreover, in this method's framework, dribbling is learned as a pass technique, in essence to and from the passer itself. It is also shown that the improvement in pass selection by our learning helps to make a team much stronger.

本文言語English
ホスト出版物のタイトルProceedings of the International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010
ページ31-35
ページ数5
出版ステータスPublished - 2010 12 1
イベントInternational MultiConference of Engineers and Computer Scientists 2010, IMECS 2010 - Kowloon, Hong Kong
継続期間: 2010 3 172010 3 19

出版物シリーズ

名前Proceedings of the International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010

Conference

ConferenceInternational MultiConference of Engineers and Computer Scientists 2010, IMECS 2010
国/地域Hong Kong
CityKowloon
Period10/3/1710/3/19

ASJC Scopus subject areas

  • コンピュータ サイエンス(その他)

フィンガープリント

「Learning of Soccer player agents using a policy gradient method: Pass selection」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