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

Harukazu Igarashi, Hitoshi Fukuoka, Seiji Ishihara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationProceedings of the International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010
Pages31-35
Number of pages5
Publication statusPublished - 2010
EventInternational MultiConference of Engineers and Computer Scientists 2010, IMECS 2010 - Kowloon
Duration: 2010 Mar 172010 Mar 19

Other

OtherInternational MultiConference of Engineers and Computer Scientists 2010, IMECS 2010
CityKowloon
Period10/3/1710/3/19

Fingerprint

Gradient methods

Keywords

  • Multi-agent system
  • Pass selection
  • Policy gradient method
  • Reinforcement learning
  • RoboCup

ASJC Scopus subject areas

  • Computer Science (miscellaneous)

Cite this

Igarashi, H., Fukuoka, H., & Ishihara, S. (2010). Learning of Soccer player agents using a policy gradient method: Pass selection. In Proceedings of the International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010 (pp. 31-35)

Learning of Soccer player agents using a policy gradient method : Pass selection. / Igarashi, Harukazu; Fukuoka, Hitoshi; Ishihara, Seiji.

Proceedings of the International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010. 2010. p. 31-35.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Igarashi, H, Fukuoka, H & Ishihara, S 2010, Learning of Soccer player agents using a policy gradient method: Pass selection. in Proceedings of the International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010. pp. 31-35, International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010, Kowloon, 10/3/17.
Igarashi H, Fukuoka H, Ishihara S. Learning of Soccer player agents using a policy gradient method: Pass selection. In Proceedings of the International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010. 2010. p. 31-35
Igarashi, Harukazu ; Fukuoka, Hitoshi ; Ishihara, Seiji. / Learning of Soccer player agents using a policy gradient method : Pass selection. Proceedings of the International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010. 2010. pp. 31-35
@inproceedings{78d61b0f15764e14b7db634b097ae590,
title = "Learning of Soccer player agents using a policy gradient method: Pass selection",
abstract = "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.",
keywords = "Multi-agent system, Pass selection, Policy gradient method, Reinforcement learning, RoboCup",
author = "Harukazu Igarashi and Hitoshi Fukuoka and Seiji Ishihara",
year = "2010",
language = "English",
isbn = "9789881701282",
pages = "31--35",
booktitle = "Proceedings of the International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010",

}

TY - GEN

T1 - Learning of Soccer player agents using a policy gradient method

T2 - Pass selection

AU - Igarashi, Harukazu

AU - Fukuoka, Hitoshi

AU - Ishihara, Seiji

PY - 2010

Y1 - 2010

N2 - 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.

AB - 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.

KW - Multi-agent system

KW - Pass selection

KW - Policy gradient method

KW - Reinforcement learning

KW - RoboCup

UR - http://www.scopus.com/inward/record.url?scp=78651570493&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78651570493&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:78651570493

SN - 9789881701282

SP - 31

EP - 35

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

ER -