Presentation 2014/5/30
Testing of several function approximations for a partially observable card game
JANA CATHRIN BACKHUS, HIDETOSHI NONAKA, TAKESHI YOSHIKAWA, MASANORI SUGIMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Game playing is considered as an important research topic in the field of Artificial Intelligence, because its features resemble those of real world problems. Research aims contain creating strong computer players for the entertainment of humans and creating human-like learning algorithms. Wizard is a partially observable multi-player card game that is structured in rounds with different grades of information imperfectness. A computer player using reinforcement learning algorithm is considered for the game. Function approximation plays an important role in reinforcement learning. In our research, we tested different function approximation approaches for the game Wizard under the aspect of having different grades of information imperfectness in the game rounds. Experimental results show that the success of the function approximations is differing a lot for the game rounds as the game winning rate of the learning agent is differing between 0% and 26.74%.
Keyword(in Japanese) (See Japanese page)
Keyword(in English)
Paper # Vol.2014-EC-32 No.14
Date of Issue

Conference Information
Committee MVE
Conference Date 2014/5/30(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 Media Experience and Virtual Environment (MVE)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Testing of several function approximations for a partially observable card game
Sub Title (in English)
Keyword(1)
1st Author's Name JANA CATHRIN BACKHUS
1st Author's Affiliation Hokkaido University()
2nd Author's Name HIDETOSHI NONAKA
2nd Author's Affiliation Hokkaido University
3rd Author's Name TAKESHI YOSHIKAWA
3rd Author's Affiliation Hokkaido University
4th Author's Name MASANORI SUGIMOTO
4th Author's Affiliation Hokkaido University
Date 2014/5/30
Paper # Vol.2014-EC-32 No.14
Volume (vol) vol.114
Number (no) 73
Page pp.pp.-
#Pages 6
Date of Issue