Infinite horizon discounted dynamic programming subject to total variation ambiguity on conditional distribution

Ioannis Tzortzis, Charalambos D. Charalambous, Themistoklis Charalambous

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

We analyze the infinite horizon minimax discounted cost Markov Control Model (MCM), for a class of controlled process conditional distributions, which belong to a ball, with respect to total variation distance metric, centered at a known nominal controlled conditional distribution with radius R ϵ [0, 2], in which the minimization is over the control strategies and the maximization is over conditional distributions. Through our analysis (i) we derive a new discounted dynamic programming equation, (ii) we show the associated contraction property, and (iii) we develop a new policy iteration algorithm. Finally, the application of the new dynamic programming and the corresponding policy iteration algorithm are shown via an illustrative example.

Original languageEnglish
Title of host publication2016 IEEE 55th Conference on Decision and Control, CDC 2016
PublisherIEEE
Pages2010-2015
Number of pages6
ISBN (Electronic)9781509018376
DOIs
Publication statusPublished - 27 Dec 2016
MoE publication typeA4 Article in a conference publication
EventIEEE Conference on Decision and Control - ARIA Resort & Casino, Las Vegas, United States
Duration: 12 Dec 201614 Dec 2016
Conference number: 55

Conference

ConferenceIEEE Conference on Decision and Control
Abbreviated titleCDC
CountryUnited States
CityLas Vegas
Period12/12/201614/12/2016

Fingerprint Dive into the research topics of 'Infinite horizon discounted dynamic programming subject to total variation ambiguity on conditional distribution'. Together they form a unique fingerprint.

  • Cite this

    Tzortzis, I., Charalambous, C. D., & Charalambous, T. (2016). Infinite horizon discounted dynamic programming subject to total variation ambiguity on conditional distribution. In 2016 IEEE 55th Conference on Decision and Control, CDC 2016 (pp. 2010-2015). [7798559] IEEE. https://doi.org/10.1109/CDC.2016.7798559