Partially Observable Markov Decision Processes With Reward Information: Basic Ideas and Models

DOI10.1109/TAC.2007.894520MaRDI QIDQ5282087zbMATH OpenFDO

Authors Cao, Xiren, Xianping Guo

Publication date 27 July 2017

Published in IEEE Transactions on Automatic Control (Search for Journal in Brave)

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Cited in

(3)

• A tutorial on partially observable Markov decision processes
• A Partially Observable Markov Decision Process with Lagged Information
• Modelling of hydrological persistence for hidden state Markov decision processes

This page was built for publication: Partially Observable Markov Decision Processes With Reward Information: Basic Ideas and Models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5282087)