Sequential decision making in non-stationary environments

We consider the problem of sequential decision making in non-stationary environments. In order to avoid solutions that are too conservative, we capture the degree of non-stationarity in real-world problems through different mathematical models for the environment. In the first model, we add to the e...

Full description

Bibliographic Details
Main Author: Yu, Jia Yuan
Other Authors: Shie Mannor (Internal/Supervisor)
Format: Others
Language:en
Published: McGill University 2010
Subjects:
Online Access:http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=92156
id ndltd-LACETR-oai-collectionscanada.gc.ca-QMM.92156
record_format oai_dc
spelling ndltd-LACETR-oai-collectionscanada.gc.ca-QMM.921562014-02-13T03:55:56ZSequential decision making in non-stationary environmentsYu, Jia YuanApplied Sciences - Operations ResearchWe consider the problem of sequential decision making in non-stationary environments. In order to avoid solutions that are too conservative, we capture the degree of non-stationarity in real-world problems through different mathematical models for the environment. In the first model, we add to the environment a state that follows Markovian dynamics subject to limited levels of non-stationary uncertainty. In the second model, we add non-stationary constraints to the environment. In the third model, we limit the frequency of non-stationary changes. In each of these models, we provide efficient learning algorithms and prove corresponding performance guarantees that depend critically on the degree of non-stationarity.Nous étudions le problème de décisions séquentielles dans des environnements non-stationnaires. Pour éviter des solutions trop conservatrices, nous modélisons le degré de non-stationnarité à travers differents modèles mathématiques de l'environnement. Dans le premier modèle, nous ajoutons à l'environnement un état qui suit une dynamique Markovienne, sujet à des niveaux limités d'incertitude non-stationnaire. Dans le second modèle, nous ajoutons des contraintes non-stationnaires à l'environnement. Dans le troisième modèle, nous limitons la fréquence des changements non-stationnaires. Pour chaque modèle, nous présentons des algorithmes d'apprentissage efficients et prouvons des guaranties de performance qui dépendent du degré de non-stationnarité. McGill UniversityShie Mannor (Internal/Supervisor)2010Electronic Thesis or Dissertationapplication/pdfenElectronically-submitted theses.All items in eScholarship@McGill are protected by copyright with all rights reserved unless otherwise indicated.Doctor of Philosophy (Department of Electrical and Computer Engineering) http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=92156
collection NDLTD
language en
format Others
sources NDLTD
topic Applied Sciences - Operations Research
spellingShingle Applied Sciences - Operations Research
Yu, Jia Yuan
Sequential decision making in non-stationary environments
description We consider the problem of sequential decision making in non-stationary environments. In order to avoid solutions that are too conservative, we capture the degree of non-stationarity in real-world problems through different mathematical models for the environment. In the first model, we add to the environment a state that follows Markovian dynamics subject to limited levels of non-stationary uncertainty. In the second model, we add non-stationary constraints to the environment. In the third model, we limit the frequency of non-stationary changes. In each of these models, we provide efficient learning algorithms and prove corresponding performance guarantees that depend critically on the degree of non-stationarity. === Nous étudions le problème de décisions séquentielles dans des environnements non-stationnaires. Pour éviter des solutions trop conservatrices, nous modélisons le degré de non-stationnarité à travers differents modèles mathématiques de l'environnement. Dans le premier modèle, nous ajoutons à l'environnement un état qui suit une dynamique Markovienne, sujet à des niveaux limités d'incertitude non-stationnaire. Dans le second modèle, nous ajoutons des contraintes non-stationnaires à l'environnement. Dans le troisième modèle, nous limitons la fréquence des changements non-stationnaires. Pour chaque modèle, nous présentons des algorithmes d'apprentissage efficients et prouvons des guaranties de performance qui dépendent du degré de non-stationnarité.
author2 Shie Mannor (Internal/Supervisor)
author_facet Shie Mannor (Internal/Supervisor)
Yu, Jia Yuan
author Yu, Jia Yuan
author_sort Yu, Jia Yuan
title Sequential decision making in non-stationary environments
title_short Sequential decision making in non-stationary environments
title_full Sequential decision making in non-stationary environments
title_fullStr Sequential decision making in non-stationary environments
title_full_unstemmed Sequential decision making in non-stationary environments
title_sort sequential decision making in non-stationary environments
publisher McGill University
publishDate 2010
url http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=92156
work_keys_str_mv AT yujiayuan sequentialdecisionmakinginnonstationaryenvironments
_version_ 1716641779540819968