31 citations · 104 across the 21 of their papers we have counts for
21 papers
A New Bound on the Cumulant Generating Function of Dirichlet Processes
Pierre Perrault, Denis Belomestny, Pierre Ménard +4
In this paper, we introduce a novel approach for bounding the cumulant generating function (CGF) of a Dirichlet process (DP) , using superadditivity. In par…
Local and adaptive mirror descents in extensive-form games
Côme Fiegel, Pierre Ménard, Tadashi Kozuno +3
We study how to learn -optimal strategies in zero-sum imperfect information games (IIG) with trajectory feedback. In this setting, players update their policies sequentially bas…
Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice
Toshinori Kitamura, Tadashi Kozuno, Yunhao Tang +12
Mirror descent value iteration (MDVI), an abstraction of Kullback-Leibler (KL) and entropy-regularized reinforcement learning (RL), has served as the basis for recent high-performi…
Learning Generative Models with Goal-conditioned Reinforcement Learning
Mariana Vargas Vieyra, Pierre Ménard
We present a novel, alternative framework for learning generative models with goal-conditioned reinforcement learning. We define two agents, a goal conditioned agent (GC-agent) and…
Adapting to game trees in zero-sum imperfect information games
Côme Fiegel, Pierre Ménard, Tadashi Kozuno +3
Imperfect information games (IIG) are games in which each player only partially observes the current game state. We study how to learn -optimal strategies in a zero-sum IIG thro…
KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal
Tadashi Kozuno, Wenhao Yang, Nino Vieillard +10
In this work, we consider and analyze the sample complexity of model-free reinforcement learning with a generative model. Particularly, we analyze mirror descent value iteration (M…
Indexed Minimum Empirical Divergence for Unimodal Bandits
Hassan Saber, Pierre Ménard, Odalric-Ambrym Maillard
We consider a multi-armed bandit problem specified by a set of one-dimensional family exponential distributions endowed with a unimodal structure. We introduce IMED-UB, a algorithm…
Adaptive Multi-Goal Exploration
Jean Tarbouriech, Omar Darwiche Domingues, Pierre Ménard +3
We introduce a generic strategy for provably efficient multi-goal exploration. It relies on AdaGoal, a novel goal selection scheme that leverages a measure of uncertainty in reachi…
Problem Dependent View on Structured Thresholding Bandit Problems
James Cheshire, Pierre Ménard, Alexandra Carpentier
We investigate the problem dependent regime in the stochastic Thresholding Bandit problem (TBP) under several shape constraints. In the TBP, the objective of the learner is to outp…
Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall
Tadashi Kozuno, Pierre Ménard, Rémi Munos +1
We study the problem of learning a Nash equilibrium (NE) in an imperfect information game (IIG) through self-play. Precisely, we focus on two-player, zero-sum, episodic, tabular II…
Bandits with many optimal arms
Rianne de Heide, James Cheshire, Pierre Ménard +1
We consider a stochastic bandit problem with a possibly infinite number of arms. We write for the proportion of optimal arms and for the minimal mean-gap between optimal…
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…
Optimal Strategies for Graph-Structured Bandits
Hassan Saber, Pierre Ménard, Odalric-Ambrym Maillard
We study a structured variant of the multi-armed bandit problem specified by a set of Bernoulli distributions with mean…
Gamification of Pure Exploration for Linear Bandits
Rémy Degenne, Pierre Ménard, Xuedong Shang +1
We investigate an active pure-exploration setting, that includes best-arm identification, in the context of linear stochastic bandits. While asymptotically optimal algorithms exist…
Fast active learning for pure exploration in reinforcement learning
Pierre Ménard, Omar Darwiche Domingues, Anders Jonsson +3
Realistic environments often provide agents with very limited feedback. When the environment is initially unknown, the feedback, in the beginning, can be completely absent, and the…
A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces
Omar Darwiche Domingues, Pierre Ménard, Matteo Pirotta +2
In this work, we propose KeRNS: an algorithm for episodic reinforcement learning in non-stationary Markov Decision Processes (MDPs) whose state-action set is endowed with a metric.…
Forced-exploration free Strategies for Unimodal Bandits
Hassan Saber, Pierre Ménard, Odalric-Ambrym Maillard
We consider a multi-armed bandit problem specified by a set of Gaussian or Bernoulli distributions endowed with a unimodal structure. Although this problem has been addressed in th…
Planning in Markov Decision Processes with Gap-Dependent Sample Complexity
Anders Jonsson, Emilie Kaufmann, Pierre Ménard +3
We propose MDP-GapE, a new trajectory-based Monte-Carlo Tree Search algorithm for planning in a Markov Decision Process in which transitions have a finite support. We prove an uppe…
Adaptive Reward-Free Exploration
Emilie Kaufmann, Pierre Ménard, Omar Darwiche Domingues +3
Reward-free exploration is a reinforcement learning setting studied by Jin et al. (2020), who address it by running several algorithms with regret guarantees in parallel. In our wo…
Fixed-Confidence Guarantees for Bayesian Best-Arm Identification
Xuedong Shang, Rianne de Heide, Emilie Kaufmann +2
We investigate and provide new insights on the sampling rule called Top-Two Thompson Sampling (TTTS). In particular, we justify its use for fixed-confidence best-arm identification…
Thresholding Bandit for Dose-ranging: The Impact of Monotonicity
Aurélien Garivier, Pierre Ménard, Laurent Rossi +1
We analyze the sample complexity of the thresholding bandit problem, with and without the assumption that the mean values of the arms are increasing. In each case, we provide a low…