Infinite horizon average cost dynamic programming subject to ambiguity on conditional distribution

Ioannis Tzortzis, Charalambos D. Charalambous, Themistoklis Charalambous

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

1 Sitaatiot (Scopus)

Abstrakti

This paper addresses the optimality of stochastic control strategies based on the infinite horizon average cost criterion, subject to total variation distance ambiguity on the conditional distribution of the controlled process. This stochastic optimal control problem is formulated using minimax theory, in which the minimization is over the control strategies and the maximization is over the conditional distributions. Under the assumption that, for every stationary Markov control law the maximizing conditional distribution of the controlled process is irreducible, we derive a new dynamic programming recursion which minimizes the future ambiguity, and we propose a new policy iteration algorithm. The new dynamic programming recursion includes, in addition to the standard terms, the oscillator semi-norm of the cost-to-go. The maximizing conditional distribution is found via a water-filling algorithm. The implications of our results are demonstrated through an example.

AlkuperäiskieliEnglanti
Otsikko2015 54th IEEE Conference on Decision and Control, CDC 2015
KustantajaIEEE
Sivut7171-7176
Sivumäärä6
Vuosikerta2016-February
ISBN (elektroninen)9781479978861
DOI - pysyväislinkit
TilaJulkaistu - 8 helmikuuta 2016
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaIEEE Conference on Decision and Control - Osaka, Japani
Kesto: 15 joulukuuta 201518 joulukuuta 2015
Konferenssinumero: 54

Conference

ConferenceIEEE Conference on Decision and Control
LyhennettäCDC
MaaJapani
KaupunkiOsaka
Ajanjakso15/12/201518/12/2015

Sormenjälki Sukella tutkimusaiheisiin 'Infinite horizon average cost dynamic programming subject to ambiguity on conditional distribution'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

  • Siteeraa tätä

    Tzortzis, I., Charalambous, C. D., & Charalambous, T. (2016). Infinite horizon average cost dynamic programming subject to ambiguity on conditional distribution. teoksessa 2015 54th IEEE Conference on Decision and Control, CDC 2015 (Vuosikerta 2016-February, Sivut 7171-7176). [7403350] IEEE. https://doi.org/10.1109/CDC.2015.7403350