75 citations · 820 across the 81 of their papers we have counts for
12 papers · 1 filter
Differentially Private Exploration in Reinforcement Learning with Linear Representation
Paul Luyo, Evrard Garcelon, Alessandro Lazaric +1
This paper studies privacy-preserving exploration in Markov Decision Processes (MDPs) with linear representation. We first consider the setting of linear-mixture MDPs (Ayoub et al.…
Top Ranking for Multi-Armed Bandit with Noisy Evaluations
Evrard Garcelon, Vashist Avadhanula, Alessandro Lazaric +1
We consider a multi-armed bandit setting where, at the beginning of each round, the learner receives noisy independent, and possibly biased, \emph{evaluations} of the true reward o…
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…
Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection
Matteo Papini, Andrea Tirinzoni, Aldo Pacchiano +3
We study the role of the representation of state-action value functions in regret minimization in finite-horizon Markov Decision Processes (MDPs) with linear structure. We first de…
Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching
Pierre-Alexandre Kamienny, Jean Tarbouriech, Sylvain Lamprier +2
Learning meaningful behaviors in the absence of reward is a difficult problem in reinforcement learning. A desirable and challenging unsupervised objective is to learn a set of div…
Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning
Denis Yarats, Rob Fergus, Alessandro Lazaric +1
We present DrQ-v2, a model-free reinforcement learning (RL) algorithm for visual continuous control. DrQ-v2 builds on DrQ, an off-policy actor-critic approach that uses data augmen…