Presentation 2004/3/12
Acceleration of game learning with reward propagation in segmented state space
Yugo NAGATA, Yu OHIGASHI, Satoru ISHIKAWA, Takashi OMORI, Koji MORIKAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Human can describe the world in discrete representations by recognizing characteristic phenomena in addition to the continuous one. It is thought that the discrete representation enables efficient problem solving. In this paper, we propose a method for finding a passing point which is important for reaching the goal by propagating the obtained reward throuhg the segmented state space. Moreover, we demonstrate that Reinforcement Learning is accelerated by setting a sub-reward at the important states found by our method in a simple video game learning.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) segmentation of state space / reinforcement learning / game learning / sub-reward
Paper # NC2003-196
Date of Issue

Conference Information
Committee NC
Conference Date 2004/3/12(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) Acceleration of game learning with reward propagation in segmented state space
Sub Title (in English)
Keyword(1) segmentation of state space
Keyword(2) reinforcement learning
Keyword(3) game learning
Keyword(4) sub-reward
1st Author's Name Yugo NAGATA
1st Author's Affiliation Faculty of Engineering, Hokkaido University()
2nd Author's Name Yu OHIGASHI
2nd Author's Affiliation Graduate School of Engineering, Hokkaido University
3rd Author's Name Satoru ISHIKAWA
3rd Author's Affiliation Graduate School of Engineering, Hokkaido University
4th Author's Name Takashi OMORI
4th Author's Affiliation Graduate School of Engineering, Hokkaido University
5th Author's Name Koji MORIKAWA
5th Author's Affiliation Advanced Technology Research Laboratory, Matsushita Electric Industrial Co.,Ltd.
Date 2004/3/12
Paper # NC2003-196
Volume (vol) vol.103
Number (no) 734
Page pp.pp.-
#Pages 6
Date of Issue