DSpace

Future University Hakodate Academic Archive >
Faculty and Students >
FUN Theses >
Doctoral Theses >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10445/6731

Title: 長遅延報酬対象向け強化学習手法
Practical reinforcement learning for long delayed reward problems
Authors: 若原, 拓己
Research Achievement Classification: 学位論文/Thesis or Dissertation
Type: Thesis or Dissertation
Peer Review: あり/yes
Solo/Joint Author(s): 単著/solo
Spage: 1
Epage: 77
Date: 10-Dec-2012
Fiscal Year: 平成24年度(2013-03修了)
Academic Degrees and number: 20103甲第21号
Degree-granting date: 2013-03-21
Degree name: 博士(システム情報科学)
Degree-granting institutions: 公立はこだて未来大学
Appears in Collections:Doctoral Theses

Files in This Item:

File Description SizeFormat
g3107007.pdf30.14 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Copyright © 2010-2012 FUTURE UNIVERSITY HAKODATE.
DSpace Software Copyright © 2002-2010  Duraspace