activity
20102026
most citedBatched bandit problems

139 citations · 615 across the 107 of their papers we have counts for

collaborators
Showing 2013Show all

6 papers · 1 filter

stat.ML2013★ 47 cited

Gaussian Process Optimization with Mutual Information

Emile Contal, Vianney Perchet, Nicolas Vayatis

In this paper, we analyze a generic algorithm scheme for sequential global optimization using Gaussian processes. The upper bounds we derive on the cumulative regret for this gener…

math.OC2013★ 1 cited

A Primal Condition for Approachability with Partial Monitoring

Shie Mannor, Vianney Perchet, Gilles Stoltz

In approachability with full monitoring there are two types of conditions that are known to be equivalent for convex sets: a primal and a dual condition. The primal one is of the f…

math.ST2013★ 21 cited

Bounded regret in stochastic multi-armed bandits

Sébastien Bubeck, Vianney Perchet, Philippe Rigollet

We study the stochastic multi-armed bandit problem when one knows the value of an optimal arm, as a well as a positive lower bound on the smallest positive gap . W…

cs.GT2013★ 5 cited

On an unified framework for approachability in games with or without signals

Vianney Perchet, Marc Quincampoix

We unify standard frameworks for approachability both in full or partial monitoring by defining a new abstract game, called the "purely informative game", where the outcome at each…

cs.GT2013

Approachability, Regret and Calibration; implications and equivalences

Vianney Perchet

Blackwell approachability, regret minimization and calibration are three criteria evaluating a strategy (or an algorithm) in different sequential decision problems, or repeated gam…

cs.GT2013

Nash equilibria with partial monitoring; Computation and Lemke-Howson algorithm

Vianney Perchet

In two player bi-matrix games with partial monitoring, actions played are not observed, only some messages are received. Those games satisfy a crucial property of usual bi-matrix g…