Reinforcement learning : an introduction

＜図書＞
Reinforcement learning : an introduction

責任表示	Richard S. Sutton and Andrew G. Barto
シリーズ	Adaptive computation and machine learning
データ種別	図書
出版情報	Cambridge, Mass. : MIT Press , c1998
本文言語	英語
大きさ	xviii, 322 p. : ill. ; 24 cm
概要	The book is divided into three parts. Part I defines the reinforcement learning problem in terms of Markov decision processes. Part II provides basic solution methods: dynamic programming, Monte Carl... methods, and temporal-difference learning. Part III presents a unified view of the solution methods and incorporates artificial neural networks, eligibility traces, and planning; the two final chapters present case studies and consider the future of reinforcement learning. 続きを見る
電子版へのリンク	https://hdl.handle.net/2324/6986198

一般注記	"A Bradford book." Bibliography: p. [291]-312 Includes index
著者標目	*Sutton, Richard S. Barto, Andrew G.
件　名	LCSH:Reinforcement learning (Machine learning)
分　類	LCC:Q325.6 DC21:006.3/1
書誌ID	1000462701
ISBN	0262193981
NCID	BA35569597
巻冊次	ISBN:0262193981
登録日	2009.09.14
更新日	2009.09.18