Limitation of Markov models and event-based learning and optimization

Xi Ren Cao*

*Corresponding author for this work

Research output: Chapter in Book/Conference Proceeding/ReportConference Paper published in a bookpeer-review

4 Citations (Scopus)

Abstract

We first illustrate the possible limitations of the widely-used Markov model and then introduce the concepts of events, event-based policies and event-based optimization. Compared with the state-based policies, event-based policies may utilize the "future" information and therefore may perform better. In addition, the number of events may scale to the system size while the number of states grows exponentially. The event-based approach is particularly efficient for systems with special structural properties. The solutions to the event-based optimization can be developed with a sensitivity-based view, which is developed recently for the area of stochastic learning and optimization.

Original languageEnglish
Title of host publicationChinese Control and Decision Conference, 2008, CCDC 2008
Pages14-17
Number of pages4
DOIs
Publication statusPublished - 2008
EventChinese Control and Decision Conference 2008, CCDC 2008 - Yantai, Shandong, China
Duration: 2 Jul 20084 Jul 2008

Publication series

NameChinese Control and Decision Conference, 2008, CCDC 2008

Conference

ConferenceChinese Control and Decision Conference 2008, CCDC 2008
Country/TerritoryChina
CityYantai, Shandong
Period2/07/084/07/08

Fingerprint

Dive into the research topics of 'Limitation of Markov models and event-based learning and optimization'. Together they form a unique fingerprint.

Cite this