Presentation 2014-01-21
An approach to develop the game agent based on Self-Organizing Map and Reinforcement learning
Keiji Kamei, Yuuki KAKIZOE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently, there have been many board game agents such as Chess and Shogi, and they could occasionally defeat professionals. The agents are able to predict possible variations of moves and their efficiencies depend on the improvement in performance of computers. At the moment our purpose is to make a game agent which has low processing ability like human beings. In this paper, we propose to apply SOM and RL for developing the game agent which plays Othello game.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Game Agent / Othello / Reversi / Reinforcement Learning / Self-Organizing Map(SOM)
Paper # NC2013-80
Date of Issue

Conference Information
Committee NC
Conference Date 2014/1/13(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) An approach to develop the game agent based on Self-Organizing Map and Reinforcement learning
Sub Title (in English)
Keyword(1) Game Agent
Keyword(2) Othello
Keyword(3) Reversi
Keyword(4) Reinforcement Learning
Keyword(5) Self-Organizing Map(SOM)
1st Author's Name Keiji Kamei
1st Author's Affiliation Graduate School of Engineering, Nishinippon Institute of Technology()
2nd Author's Name Yuuki KAKIZOE
2nd Author's Affiliation Graduate School of Engineering, Nishinippon Institute of Technology
Date 2014-01-21
Paper # NC2013-80
Volume (vol) vol.113
Number (no) 382
Page pp.pp.-
#Pages 6
Date of Issue