31 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Afterschool AllianceUS13 papers
- Centre de Recherche en Informatique, Signal et Automatique de LilleFR9 papers
- Centre de Recherche en InformatiqueFR6 papers
- Centre National de la Recherche ScientifiqueFR6 papers
- Université de LilleFR6 papers
- Google DeepMind (United Kingdom)GB3 papers
- Institut national de recherche en sciences et technologies du numériqueFR3 papers
- Chalmers University of TechnologySE2 papers
- École Centrale de LilleFR2 papers
- National University of SingaporeSG2 papers
- Otto-von-Guericke-Universität MagdeburgDE2 papers
- University of OsloNO2 papers
21 papers
Risk-aware linear bandits with convex loss
Patrick Saux, Odalric-Ambrym Maillard
In decision-making problems such as the multi-armed bandit, an agent learns sequentially by optimizing a certain feedback. While the mean reward criterion has been extensively stud…
Choosing Answers in -Best-Answer Identification for Linear Bandits
Marc Jourdan, Rémy Degenne
In pure-exploration problems, information is gathered sequentially to answer a question on the stochastic environment. While best-arm identification for linear bandits has been ext…
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…
How Biased are Your Features?: Computing Fairness Influence Functions with Global Sensitivity Analysis
Bishwamittra Ghosh, Debabrota Basu, Kuldeep S. Meel
Fairness in machine learning has attained significant focus due to the widespread application in high-stake decision-making tasks. Unregulated machine learning classifiers can exhi…
Bandits Corrupted by Nature: Lower Bounds on Regret and Robust Optimistic Algorithm
Debabrota Basu, Odalric-Ambrym Maillard, Timothée Mathieu
We study the corrupted bandit problem, i.e. a stochastic multi-armed bandit problem with unknown reward distributions, which are heavy-tailed and corrupted by a history-indepen…
Bregman Deviations of Generic Exponential Families
Sayak Ray Chowdhury, Patrick Saux, Odalric-Ambrym Maillard +1
We revisit the method of mixture technique, also known as the Laplace method, to study the concentration phenomenon in generic exponential families. Combining the properties of Bre…
From Optimality to Robustness: Dirichlet Sampling Strategies in Stochastic Bandits
Dorian Baudry, Patrick Saux, Odalric-Ambrym Maillard
The stochastic multi-arm bandit problem has been extensively studied under standard assumptions on the arm's distribution (e.g bounded with known support, exponential family, etc).…
Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint
Matthieu Geist, Julien Pérolat, Mathieu Laurière +5
Concave Utility Reinforcement Learning (CURL) extends RL from linear to concave utilities in the occupancy measure induced by the agent's policy. This encompasses not only RL but a…
Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret
Jean Tarbouriech, Runlong Zhou, Simon S. Du +3
We study the problem of learning in the stochastic shortest path (SSP) setting, where an agent seeks to minimize the expected cost accumulated before reaching a goal state. We desi…
Concentration study of M-estimators using the influence function
Timothée Mathieu
We present a new finite-sample analysis of M-estimators of locations in using the tool of the influence function. In particular, we show that the deviations of an M-…
Offline Reinforcement Learning with Pseudometric Learning
Robert Dadashi, Shideh Rezaeifar, Nino Vieillard +3
Offline Reinforcement Learning methods seek to learn a policy from logged transitions of an environment, without any interaction. In the presence of function approximation, and und…
UCB Momentum Q-learning: Correcting the bias without forgetting
Pierre Menard, Omar Darwiche Domingues, Xuedong Shang +1
We propose UCBMQ, Upper Confidence Bound Momentum Q-learning, a new algorithm for reinforcement learning in tabular and possibly stage-dependent, episodic Markov decision process.…
On Meritocracy in Optimal Set Selection
Thomas Kleine Buening, Meirav Segal, Debabrota Basu +2
Typically, merit is defined with respect to some intrinsic measure of worth. We instead consider a setting where an individual's worth is \emph{relative}: when a Decision Maker (DM…
SENTINEL: Taming Uncertainty with Ensemble-based Distributional Reinforcement Learning
Hannes Eriksson, Debabrota Basu, Mina Alibeigi +1
In this paper, we consider risk-sensitive sequential decision-making in Reinforcement Learning (RL). Our contributions are two-fold. First, we introduce a novel and coherent quanti…
Optimal Thompson Sampling strategies for support-aware CVaR bandits
Dorian Baudry, Romain Gautron, Emilie Kaufmann +1
In this paper we study a multi-arm bandit problem in which the quality of each arm is measured by the Conditional Value at Risk (CVaR) at some level alpha of the reward distributio…
Stochastic Bandits with Vector Losses: Minimizing -Norm of Relative Losses
Xuedong Shang, Han Shao, Jian Qian
Multi-armed bandits are widely applied in scenarios like recommender systems, for which the goal is to maximize the click rate. However, more factors should be considered, e.g., us…
Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited
Omar Darwiche Domingues, Pierre Ménard, Emilie Kaufmann +1
In this paper, we propose new problem-independent lower bounds on the sample complexity and regret in episodic MDPs, with a particular focus on the non-stationary case in which the…
Learning Value Functions in Deep Policy Gradients using Residual Variance
Yannis Flet-Berliac, Reda Ouhamma, Odalric-Ambrym Maillard +1
Policy gradient algorithms have proven to be successful in diverse decision making and control tasks. However, these methods suffer from high sample complexity and instability issu…
Justicia: A Stochastic SAT Approach to Formally Verify Fairness
Bishwamittra Ghosh, Debabrota Basu, Kuldeep S. Meel
As a technology ML is oblivious to societal good or bad, and thus, the field of fair machine learning has stepped up to propose multiple mathematical definitions, algorithms, and s…
Improved Exploration in Factored Average-Reward MDPs
Mohammad Sadegh Talebi, Anders Jonsson, Odalric-Ambrym Maillard
We consider a regret minimization task under the average-reward criterion in an unknown Factored Markov Decision Process (FMDP). More specifically, we consider an FMDP where the st…
A Practical Algorithm for Multiplayer Bandits when Arm Means Vary Among Players
Etienne Boursier, Emilie Kaufmann, Abbas Mehrabian +1
We study a multiplayer stochastic multi-armed bandit problem in which players cannot communicate, and if two or more players pull the same arm, a collision occurs and the involved…