Emilie Kaufmann

research

∙ 07/01/2023

Adaptive Algorithms for Relaxed Pareto Set Identification

In this paper we revisit the fixed-confidence identification of the Pare...

0 Cyrille Kone, et al. ∙

research

∙ 06/23/2023

Active Coverage for PAC Reinforcement Learning

Collecting and leveraging data with good coverage properties plays a cru...

0 Aymen Al Marjani, et al. ∙

research

∙ 05/25/2023

An ε-Best-Arm Identification Algorithm for Fixed-Confidence and Beyond

We propose EB-TCε, a novel sampling rule for ε-best arm identification i...

0 Marc Jourdan, et al. ∙

research

∙ 10/03/2022

Dealing with Unknown Variances in Best-Arm Identification

The problem of identifying the best arm among a collection of items havi...

10 Marc Jourdan, et al. ∙

research

∙ 07/12/2022

Optimistic PAC Reinforcement Learning: the Instance-Dependent View

Optimistic algorithms have been extensively studied for regret minimizat...

0 Andrea Tirinzoni, et al. ∙

research

∙ 06/13/2022

Top Two Algorithms Revisited

Top Two algorithms arose as an adaptation of Thompson sampling to best a...

14 Marc Jourdan, et al. ∙

research

∙ 05/31/2022

Near-Optimal Collaborative Learning in Bandits

This paper introduces a general multi-agent bandit model in which each a...

0 Clémence Réda, et al. ∙

research

∙ 03/21/2022

Efficient Algorithms for Extreme Bandits

In this paper, we contribute to the Extreme Bandit problem, a variant of...

3 Dorian Baudry, et al. ∙

research

∙ 03/17/2022

Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs

In probably approximately correct (PAC) reinforcement learning (RL), an ...

0 Andrea Tirinzoni, et al. ∙

research

∙ 03/18/2021

Top-m identification for linear bandits

Motivated by an application to drug repurposing, we propose the first al...

0 Clémence Réda, et al. ∙

research

∙ 12/10/2020

Thompson Sampling for CVaR Bandits

Risk awareness is an important feature to formulate a variety of real wo...

0 Dorian Baudry, et al. ∙

research

∙ 10/27/2020

Sub-sampling for Efficient Non-Parametric Bandit Exploration

In this paper we propose the first multi-armed bandit algorithm based on...

0 Dorian Baudry, et al. ∙

research

∙ 10/07/2020

Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited

In this paper, we propose new problem-independent lower bounds on the sa...

0 Omar Darwiche Domingues, et al. ∙

research

∙ 07/27/2020

Fast active learning for pure exploration in reinforcement learning

Realistic environments often provide agents with very limited feedback. ...

10 Pierre Ménard, et al. ∙

research

∙ 07/09/2020

A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces

In this work, we propose KeRNS: an algorithm for episodic reinforcement ...

51 Omar Darwiche Domingues, et al. ∙

research

∙ 06/11/2020

Adaptive Reward-Free Exploration

Reward-free exploration is a reinforcement learning setting recently stu...

3 Emilie Kaufmann, et al. ∙

research

∙ 06/10/2020

Planning in Markov Decision Processes with Gap-Dependent Sample Complexity

We propose MDP-GapE, a new trajectory-based Monte-Carlo Tree Search algo...

10 Anders Jonsson, et al. ∙

research

∙ 04/12/2020

Regret Bounds for Kernel-Based Reinforcement Learning

We consider the exploration-exploitation dilemma in finite-horizon reinf...

0 Omar Darwiche Domingues, et al. ∙

research

∙ 12/06/2019

Solving Bernoulli Rank-One Bandits with Unimodal Thompson Sampling

Stochastic Rank-One Bandits (Katarya et al, (2017a,b)) are a simple fram...

0 Cindy Trinh, et al. ∙

research

∙ 10/24/2019

Fixed-Confidence Guarantees for Bayesian Best-Arm Identification

We investigate and provide new insights on the sampling rule called Top-...

0 Xuedong Shang, et al. ∙

research

∙ 05/09/2019

Non-Asymptotic Sequential Tests for Overlapping Hypotheses and application to near optimal arm identification in bandit models

In this paper, we study sequential testing problems with overlapping hyp...

0 Aurélien Garivier, et al. ∙

research

∙ 03/17/2019

On Multi-Armed Bandit Designs for Phase I Clinical Trials

We study the problem of finding the optimal dosage in a phase I clinical...

0 Maryam Aziz, et al. ∙

research

∙ 02/05/2019

The Generalized Likelihood Ratio Test meets klUCB: an Improved Algorithm for Piece-Wise Non-Stationary Bandits

We propose a new algorithm for the piece-wise non-stationary bandit pro...

0 Lilian Besson, et al. ∙

research

∙ 02/04/2019

New Algorithms for Multiplayer Bandits when Arm Means Vary Among Players

We study multiplayer stochastic multi-armed bandit problems in which the...

0 Emilie Kaufmann, et al. ∙

research

∙ 11/28/2018

Mixture Martingales Revisited with Applications to Sequential Tests and Confidence Intervals

This paper presents new deviation inequalities that are valid uniformly ...

0 Emilie Kaufmann, et al. ∙

research

∙ 07/02/2018

Multi-Armed Bandit Learning in IoT Networks: Learning helps even in non-stationary settings

Setting up the future Internet of Things (IoT) networks will require to ...

0 Rémi Bonnefoi, et al. ∙

research

∙ 06/04/2018

Sequential Test for the Lowest Mean: From Thompson to Murphy Sampling

Learning the minimum/maximum mean among a finite set of distributions is...

0 Emilie Kaufmann, et al. ∙

research

∙ 03/19/2018

What Doubling Tricks Can and Can't Do for Multi-Armed Bandits

An online reinforcement learning algorithm is anytime if it does not nee...

0 Lilian Besson, et al. ∙

research

∙ 03/13/2018

Pure Exploration in Infinitely-Armed Bandit Models with Fixed-Confidence

We consider the problem of near-optimal arm identification in the fixed ...

0 Maryam Aziz, et al. ∙

research

∙ 11/07/2017

Multi-Player Bandits Models Revisited

Multi-player Multi-Armed Bandits (MAB) have been extensively studied in ...

0 Lilian Besson, et al. ∙

research

∙ 08/16/2017

Corrupt Bandits for Preserving Local Privacy

We study a variant of the stochastic multi-armed bandit (MAB) problem in...

0 Pratik Gajane, et al. ∙

research

∙ 06/09/2017

Monte-Carlo Tree Search by Best Arm Identification

Recent advances in bandit tools and techniques for sequential learning a...

0 Emilie Kaufmann, et al. ∙

research

∙ 01/31/2017

Learning the distribution with largest mean: two bandit frameworks

Over the past few years, the multi-armed bandit model has become increas...

0 Emilie Kaufmann, et al. ∙

research

∙ 06/30/2016

Asymptotically Optimal Algorithms for Budgeted Multiple Play Bandits

We study a generalization of the multi-armed bandit problem with multipl...

0 Alexander Luedtke, et al. ∙

research

∙ 02/15/2016

Maximin Action Identification: A New Bandit Framework for Games

We study an original problem of pure exploration in a strategic bandit m...

0 Aurélien Garivier, et al. ∙

research

∙ 02/15/2016

Optimal Best Arm Identification with Fixed Confidence

We give a complete characterization of the complexity of best-arm identi...

0 Aurélien Garivier, et al. ∙

research

∙ 01/06/2016

On Bayesian index policies for sequential resource allocation

This paper is about index policies for minimizing (frequentist) regret i...

0 Emilie Kaufmann, et al. ∙

research

∙ 06/12/2015

A Spectral Algorithm with Additive Clustering for the Recovery of Overlapping Communities in Networks

This paper presents a novel spectral algorithm with additive clustering ...

0 Emilie Kaufmann, et al. ∙

research

∙ 07/16/2014

On the Complexity of Best Arm Identification in Multi-Armed Bandit Models

The stochastic multi-armed bandit model is a simple abstraction that has...

0 Emilie Kaufmann, et al. ∙

research

∙ 05/13/2014

On the Complexity of A/B Testing

A/B testing refers to the task of determining the best option among two ...

0 Emilie Kaufmann, et al. ∙

research

∙ 07/12/2013

Thompson Sampling for 1-Dimensional Exponential Family Bandits

Thompson Sampling has been demonstrated in many complex bandit models, h...

0 Nathaniel Korda, et al. ∙

research

∙ 05/18/2012

Thompson Sampling: An Asymptotically Optimal Finite Time Analysis

The question of the optimality of Thompson Sampling for solving the stoc...

0 Emilie Kaufmann, et al. ∙

Emilie Kaufmann

Featured Co-authors