ヒラオカ　カズユキ   HIRAOKA Kazuyuki   平岡　和幸    所属   経営学部 データサイエンス学科    職種   教授
言語種別	英語
発行・発表の年月	2009/03
形態種別	学術雑誌
査読	査読あり
標題	Parallel reinforcement learning for weighted multi-criteria model with adaptive margin
執筆形態	共著
掲載誌名	Cognitive Neurodynamics
掲載区分	国外
巻・号・頁	3(1),pp.17-24
著者・共著者	Kazuyuki Hiraoka,Manabu Yoshida,Taketoshi Mishima
概要	Reinforcement learning (RL) for a linear family of tasks is described in this paper. The key of our discussion is nonlinearity of the optimal solution even if the task family is linear we cannot obtain the optimal policy using a naive approach. Although an algorithm exists for calculating the equivalent result to Q-learning for each task simultaneously, it presents the problem of explosion of set sizes. We therefore introduce adaptive margins to overcome this difficulty. © 2008 Springer Science+Business Media B.V.
DOI	10.1007/s11571-008-9066-9
ISSN	1871-4080