Strategies for prediction under imperfect monitoring

Gabor Lugosi (), Shie Mannor () and Gilles Stoltz
Additional contact information
Gabor Lugosi: ICREA - Institució Catalana de Recerca i Estudis Avançats = Catalan Institution for Research and Advanced Studies
Shie Mannor: McGill University = Université McGill [Montréal, Canada]

Post-Print from HAL

Abstract: We propose simple randomized strategies for sequential prediction under imperfect monitoring, that is, when the forecaster does not have access to the past outcomes but rather to a feedback signal. The proposed strategies are consistent in the sense that they achieve, asymptotically, the best possible average reward. It was Rustichini (1999) who first proved the existence of such consistent predictors. The forecasters presented here offer the first constructive proof of consistency. Moreover, the proposed algorithms are computationally efficient. We also establish upper bounds for the rates of convergence. In the case of deterministic feedback, these rates are optimal up to logarithmic terms.

Keywords: individual sequences; repeated games with partial monitoring; approachability (search for similar items in EconPapers)
Date: 2008
Note: View the original document on HAL open archive server: https://hal.science/hal-00124679v4
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (4)

Published in Mathematics of Operations Research, 2008, à paraître

Downloads: (external link)
https://hal.science/hal-00124679v4/document (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-00124679

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().