Robust approachability and regret minimization in games with partial monitoring - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2012

Robust approachability and regret minimization in games with partial monitoring

Abstract

Approachability has become a standard tool in analyzing earning algorithms in the adversarial online learning setup. We develop a variant of approachability for games where there is ambiguity in the obtained reward that belongs to a set, rather than being a single vector. Using this variant we tackle the problem of approachability in games with partial monitoring and develop simple and efficient algorithms (i.e., with constant per-step complexity) for this setup. We finally consider external regret and internal regret in repeated games with partial monitoring and derive regret-minimizing strategies based on approachability theory.
Fichier principal
Vignette du fichier
Mannor-Perchet-Stoltz--Robust-Approachability--HAL.pdf (497.55 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00595695 , version 1 (25-05-2011)
hal-00595695 , version 2 (29-08-2011)
hal-00595695 , version 3 (15-02-2012)

Identifiers

Cite

Shie Mannor, Vianney Perchet, Gilles Stoltz. Robust approachability and regret minimization in games with partial monitoring. 2012. ⟨hal-00595695v3⟩
378 View
267 Download

Altmetric

Share

Gmail Facebook X LinkedIn More