文献
J-GLOBAL ID:201702262754135899
整理番号:17A1624769
Gauss過程を用いた連続時間Markov決定過程における政策学習【Powered by NICT】
Policy learning in continuous-time Markov decision processes using Gaussian Processes
著者 (8件):
Bartocci Ezio
(Faculty of Informatics, Vienna University of Technology, Austria)
,
Bortolussi Luca
(Department of Maths and Geosciences, University of Trieste, Italy)
,
Bortolussi Luca
(CNR/ISTI, Pisa, Italy)
,
Bortolussi Luca
(Modelling and Simulation Group, Saarland University, Germany)
,
Brazdil Tomas
(Faculty of Informatics, Masaryk University, Czech Republic)
,
Milios Dimitrios
(School of Informatics, University of Edinburgh, UK)
,
Sanguinetti Guido
(School of Informatics, University of Edinburgh, UK)
,
Sanguinetti Guido
(SynthSys, Centre for Synthetic and Systems Biology, University of Edinburgh, UK)
資料名:
Performance Evaluation
(Performance Evaluation)
巻:
116
ページ:
84-100
発行年:
2017年
JST資料番号:
C0647B
ISSN:
0166-5316
CODEN:
PEEVD9
資料種別:
逐次刊行物 (A)
記事区分:
原著論文
発行国:
オランダ (NLD)
言語:
英語 (EN)