Presentation	2000/7/11 Learning of minimax strategy by a support vector machine Hirotaka Niitsuma, Shin Ishii,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	In this article, we propose a method to acquire a state-value function of the minimax strategy, using a support vector machine(SVM). Our method can be applied to tasks whose state is represented by a bit row. Examples are games. We apply our method to the game of'Tic-Tac-Toe'. By introducing a kernel function based on bit operations, efficient computation is achieved. Consequently, SVM obtains the compressed representation of the state-value function. The trained player can then retrieve the compressed state-value function efficiently.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	support vector machine / Tic-Tac-Toe / bit board / minimax strategy
Paper #	NC2000-50
Date of Issue

Conference Information
Committee	NC
Conference Date	2000/7/11(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)	Learning of minimax strategy by a support vector machine
Sub Title (in English)
Keyword(1)	support vector machine
Keyword(2)	Tic-Tac-Toe
Keyword(3)	bit board
Keyword(4)	minimax strategy
1st Author's Name	Hirotaka Niitsuma
1st Author's Affiliation	CREST, Japan Science and Technology Corporation()
2nd Author's Name	Shin Ishii
2nd Author's Affiliation	Nara institute of Science and Technology:CREST, Japan Science and Technology Corporation
Date	2000/7/11
Paper #	NC2000-50
Volume (vol)	vol.100
Number (no)	191
Page	pp.pp.-
#Pages	8
Date of Issue