Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/73573
Title: Lightning does not strike twice: Robust MDPs with coupled uncertainty
Authors: Mannor, S.
Mebel, O.
Xu, H. 
Issue Date: 2012
Source: Mannor, S.,Mebel, O.,Xu, H. (2012). Lightning does not strike twice: Robust MDPs with coupled uncertainty. Proceedings of the 29th International Conference on Machine Learning, ICML 2012 1 : 385-392. ScholarBank@NUS Repository.
Abstract: We consider Markov decision processes under parameter uncertainty. Previous studies all restrict to the case that uncertainties among different states are uncoupled, which leads to conservative solutions. In contrast, we introduce an intuitive concept, termed "Lightning Does not Strike Twice," to model coupled uncertain parameters. Specifically, we require that the system can deviate from its nominal parameters only a bounded number of times. We give probabilistic guarantees indicating that this model represents real life situations and devise tractable algorithms for computing optimal control policies. Copyright 2012 by the author(s)/owner(s).
Source Title: Proceedings of the 29th International Conference on Machine Learning, ICML 2012
URI: http://scholarbank.nus.edu.sg/handle/10635/73573
ISBN: 9781450312851
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

20
checked on Dec 9, 2017

Google ScholarTM

Check


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