688 citations · 1.3k across the 44 of their papers we have counts for
22 papers · 1 filter
Towards Instance-Optimality in Online PAC Reinforcement Learning
Aymen Al-Marjani, Andrea Tirinzoni, Emilie Kaufmann
Several recent works have proposed instance-dependent upper bounds on the number of episodes needed to identify, with probability , an -optimal policy in finite-h…
Adaptive Algorithms for Relaxed Pareto Set Identification
Cyrille Kone, Emilie Kaufmann, Laura Richert
In this paper we revisit the fixed-confidence identification of the Pareto optimal set in a multi-objective multi-armed bandit model. As the sample complexity to identify the exact…
An -Best-Arm Identification Algorithm for Fixed-Confidence and Beyond
Marc Jourdan, Rémy Degenne, Emilie Kaufmann
We propose EB-TC, a novel sampling rule for -best arm identification in stochastic bandits. It is the first instance of Top Two algorithm analyzed for app…
Dealing with Unknown Variances in Best-Arm Identification
Marc Jourdan, Rémy Degenne, Emilie Kaufmann
The problem of identifying the best arm among a collection of items having Gaussian rewards distribution is well understood when the variances are known. Despite its practical rele…
Top Two Algorithms Revisited
Marc Jourdan, Rémy Degenne, Dorian Baudry +2
Top Two algorithms arose as an adaptation of Thompson sampling to best arm identification in multi-armed bandit models (Russo, 2016), for parametric families of arms. They select t…
Sub-sampling for Efficient Non-Parametric Bandit Exploration
Dorian Baudry, Emilie Kaufmann, Odalric-Ambrym Maillard
In this paper we propose the first multi-armed bandit algorithm based on re-sampling that achieves asymptotically optimal regret simultaneously for different families of arms (name…